© 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. 104158
    Prev
    Next
    INDEX
    Explanations

    first edition, signed, hardcover

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

    damage and consequence

    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
    uğ
    0.47
    哦
    0.45
    વાની
    0.44
    屎
    0.44
    િ
    0.43
    વામાં
    0.43
    🦆
    0.43
    碼
    0.43
    方的
    0.42
    那我們
    0.42
    POSITIVE LOGITS
     tred
    0.46
     antelope
    0.46
     geranium
    0.45
     cypress
    0.44
     Etr
    0.44
     stages
    0.43
    udir
    0.43
     cumulative
    0.42
     eccentric
    0.42
     pertemuan
    0.42
    Activations Density 0.000%

    No Known Activations