© 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. 10-GEMMASCOPE-RES-131K
    7. 103506
    Prev
    Next
    INDEX
    Explanations

    have a/an/two

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

    the presence of standalone numbers or numeric tokens in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     I
    -2.39
    ↵
    -2.25
     when
    -2.11
    3
    -2.08
    6
    -2.05
     if
    -2.00
    1
    -1.97
    5
    -1.90
    ↵↵
    -1.86
    7
    -1.84
    POSITIVE LOGITS
     bottes
    1.54
    瓛
    1.52
     sonidos
    1.51
     them
    1.49
     résist
    1.47
    rógeno
    1.46
     menangis
    1.42
     menyadari
    1.41
     noirs
    1.41
    擼
    1.41
    Activations Density 0.183%

    No Known Activations