© 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. 20845
    Prev
    Next
    INDEX
    Explanations

    uk and code documentation

    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
     C
    0.41
     Precinct
    0.39
    ał
    0.39
     Room
    0.38
    C
    0.38
    jacket
    0.37
     atent
    0.37
    variation
    0.36
     Survey
    0.36
    :
    0.36
    POSITIVE LOGITS
     එක්
    0.43
     voix
    0.41
    ティー
    0.40
    銠
    0.40
     មាន
    0.40
     Ừ
    0.40
    🫢
    0.39
    🦋
    0.39
     trzy
    0.39
    🫣
    0.39
    Activations Density 0.000%

    No Known Activations