© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 223368
    Prev
    Next
    INDEX
    Explanations

    sc followed by library names

    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_40_width_262k_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
     היה
    0.51
     midfielders
    0.48
    ెస్
    0.48
    erà
    0.42
     微
    0.42
    錢
    0.41
     robes
    0.40
     lebt
    0.40
    क्रो
    0.40
    👦
    0.40
    POSITIVE LOGITS
    iggle
    0.52
     scarcity
    0.52
     scramble
    0.49
     script
    0.47
    scoreboard
    0.45
     scope
    0.45
    yt
    0.44
     Sc
    0.43
    ync
    0.42
    affold
    0.42
    Activations Density 0.010%

    No Known Activations