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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103786
    Prev
    Next
    INDEX
    Explanations

    human person, most unusual

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

    The neuron is acting as a positional counter, firing more strongly the further into the document (i.e. for tokens at higher positions).

    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
     daft
    -1.03
     australis
    -1.02
     '
    -0.99
     humorous
    -0.97
    小白
    -0.96
    垦
    -0.96
    ´
    -0.94
     –
    -0.94
     infamous
    -0.93
    ímos
    -0.93
    POSITIVE LOGITS
    tumblr
    1.16
    Fuck
    1.13
     também
    1.13
     plz
    1.13
     fucking
    1.13
    Basically
    1.12
     bardzo
    1.11
    ！！！！！
    1.11
    全然
    1.11
     necessitate
    1.09
    Activations Density 0.248%

    No Known Activations