© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11294
    Prev
    Next
    INDEX
    Explanations

    self-deprecation or lack of skill

    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_22/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
     their
    -0.97
    曖昧さ回避
    -0.94
    umą
    -0.94
     themselves
    -0.91
    店内は
    -0.90
    渟
    -0.88
     tisch
    -0.86
     ihnen
    -0.86
    当店
    -0.85
     nigga
    -0.85
    POSITIVE LOGITS
     my
    1.50
     I
    1.14
    failed
    1.09
    dification
    1.09
     myself
    1.08
     but
    1.00
     pathetic
    0.96
     sencillas
    0.95
     lame
    0.95
    ckle
    0.94
    Activations Density 0.125%

    No Known Activations