© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63308
    Prev
    Next
    INDEX
    Explanations

    programming identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.48
    わけで
    -1.30
    にしました
    -1.23
    為に
    -1.17
    ⸒
    -1.14
     として
    -1.12
    なのだ
    -1.09
    ところに
    -1.06
    のご紹介
    -1.05
    __':
    
    -1.03
    POSITIVE LOGITS
    これは
    1.14
    p
    1.02
    лле
    0.98
    but
    0.97
     Verpflichtung
    0.96
    ❳
    0.96
     mouseY
    0.95
     همچنین
    0.95
    inafter
    0.95
    ですが
    0.94
    Activations Density 0.020%

    No Known Activations