© 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. 10-GEMMASCOPE-RES-131K
    7. 39519
    Prev
    Next
    INDEX
    Explanations

    certain [noun]

    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_10/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
     vanno
    -1.34
     vectorielle
    -1.29
    這一
    -1.28
     étrang
    -1.28
     sembrano
    -1.23
     where
    -1.23
    视着
    -1.20
     Passwort
    -1.15
     اين
    -1.14
    嗆
    -1.14
    POSITIVE LOGITS
     antes
    1.18
     
    1.18
     прекрасно
    1.18
     four
    1.16
     many
    1.15
     ABBREVIATIONS
    1.14
    ndrome
    1.13
    issionais
    1.13
    unnamed
    1.12
    ₫
    1.12
    Activations Density 0.030%

    No Known Activations