© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15831
    Prev
    Next
    INDEX
    Explanations

    never or not yet

    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
    ㄓ
    -0.89
     соответству
    -0.82
    そういえば
    -0.82
     каждой
    -0.81
     größer
    -0.81
     zároveň
    -0.81
    Ern
    -0.79
     ギフト
    -0.78
     предыду
    -0.78
    héro
    -0.78
    POSITIVE LOGITS
     never
    2.16
     nunca
    1.71
     jamais
    1.52
    never
    1.49
    永远
    1.48
     forever
    1.46
     eventually
    1.41
     Never
    1.38
    Never
    1.37
     Nunca
    1.33
    Activations Density 0.064%

    No Known Activations