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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2002
    Prev
    Next
    INDEX
    Explanations

    Dynamic Link Library (`DLL`) and attackers

    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
     pairings
    0.48
    자
    0.47
     artworks
    0.46
    したい
    0.43
     telephones
    0.43
     घण्ट
    0.43
    IDAY
    0.42
     Tennyson
    0.42
    ㍍
    0.42
     dicembre
    0.42
    POSITIVE LOGITS
     *
    0.54
     $
    0.52
     \*
    0.50
     **
    0.47
    ^{
    0.47
    egal
    0.47
    endung
    0.47
     bend
    0.46
    istencia
    0.46
    égalité
    0.46
    Activations Density 0.002%

    No Known Activations