© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31909
    Prev
    Next
    INDEX
    Explanations

    stimulus presentation

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron doesn’t pick out any semantic or orthographic feature of the words themselves but rather tracks how far into the document a token occurs—its activation rises roughly in proportion to the token’s position.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seksi
    -1.06
     宣传
    -1.02
    ilization
    -1.02
    inę
    -0.96
     anormal
    -0.94
     журнали
    -0.94
     tử
    -0.93
     mikro
    -0.93
    tych
    -0.92
    Expressions
    -0.90
    POSITIVE LOGITS
     presented
    1.59
     stimulus
    1.48
     presentation
    1.43
     experimenter
    1.42
     stimuli
    1.36
     предъ
    1.36
     cues
    1.20
    提示
    1.14
     task
    1.11
     presentations
    1.09
    Activations Density 0.179%

    No Known Activations