Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 36446
    Prev
    Next
    INDEX
    Explanations

    common, logical connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alja
    0.50
     Hadamard
    0.50
    Gosudarstvennyj
    0.48
    hiddenMap
    0.47
    ಙ
    0.47
    classteacher
    0.44
    pieceSelection
    0.44
    СТЬ
    0.44
     کازخستان
    0.44
     tannin
    0.43
    POSITIVE LOGITS
     en
    0.51
    {
    0.50
     una
    0.48
    一種
    0.47
    T
    0.46
    :
    0.46
    *
    0.45
     expos
    0.45
    S
    0.44
    \
    0.44
    Activations Density 0.009%

    No Known Activations