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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20462
    Prev
    Next
    INDEX
    Explanations

    drew parallels, translations, sound, spiritual, embossing

    np_acts-logits-general · gemini-2.5-flash-lite

    causal discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     フル
    0.51
     Lebens
    0.50
    וד
    0.48
    種類の
    0.48
     オン
    0.48
     IMPORTANT
    0.48
     Familie
    0.48
    琭
    0.48
    謾
    0.47
    лари
    0.47
    POSITIVE LOGITS
    le
    0.47
    istic
    0.46
     hovered
    0.45
    lee
    0.45
    zones
    0.44
    나
    0.44
    bar
    0.43
    Dragged
    0.43
    नगर
    0.43
    _{
    0.42
    Activations Density 0.000%

    No Known Activations