© 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. 59616
    Prev
    Next
    INDEX
    Explanations

    I wish I had

    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
    ︓
    -1.24
     الماء
    -1.21
     sollten
    -1.20
    ميل
    -1.20
    }}{{
    -1.18
    مين
    -1.18
    ⸙
    -1.18
    垕
    -1.16
    datable
    -1.16
     SHOULD
    -1.15
    POSITIVE LOGITS
     use
    1.41
     there
    1.29
     here
    1.23
     it
    1.22
    是他
    1.19
     same
    1.16
     utilização
    1.13
     опыта
    1.12
    .”
    1.09
     visit
    1.05
    Activations Density 0.053%

    No Known Activations