© 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. 133691
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    spreading
    0.47
     gossip
    0.40
    TV
    0.40
    лау
    0.39
     أح
    0.39
    益
    0.39
    anth
    0.39
     spreading
    0.39
    了一些
    0.39
    CAT
    0.38
    POSITIVE LOGITS
    兵庫
    0.38
    聖
    0.38
     organics
    0.37
     coworking
    0.36
    vertexBuffer
    0.35
     guaranteed
    0.34
     dynamo
    0.34
     zoom
    0.34
    Zoom
    0.34
     sulfuric
    0.34
    Activations Density 0.000%

    No Known Activations