© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108756
    Prev
    Next
    INDEX
    Explanations

    quoted dialogue openers

    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
    Далее
    -0.89
    引导
    -0.83
     it
    -0.79
     łóż
    -0.77
    alth
    -0.77
     FURN
    -0.77
    sili
    -0.76
    你先
    -0.76
     langit
    -0.76
     년
    -0.76
    POSITIVE LOGITS
    Hey
    3.61
     hey
    3.53
     Hey
    3.47
    hey
    3.06
    HEY
    2.25
     HEY
    2.19
    喂
    1.67
     dude
    1.46
    Oi
    1.39
     listen
    1.35
    Activations Density 0.022%

    No Known Activations