© 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-262K
    4. 4105
    Prev
    Next
    INDEX
    Explanations

    work you, definition of, reform envelopes, classifications that, through the, prompt or, storage you, total planned

    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_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
     стол
    0.46
    \,.
    0.44
     電力
    0.43
    𝘋
    0.43
     вну
    0.42
     服务
    0.41
    urón
    0.41
     서비스를
    0.41
     தண்ணீர்
    0.40
     근무
    0.40
    POSITIVE LOGITS
    h
    0.42
     released
    0.42
     restricted
    0.41
     Unpublished
    0.41
    ="#
    0.41
     I
    0.40
     at
    0.40
     states
    0.40
     circular
    0.40
    =
    0.40
    Activations Density 0.000%

    No Known Activations