© 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. 22-GEMMASCOPE-RES-131K
    7. 34987
    Prev
    Next
    INDEX
    Explanations

    job title roles

    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
    ͛
    -1.32
     хоте
    -1.30
    盉
    -1.29
    andering
    -1.23
    licante
    -1.23
     they
    -1.20
     szkoły
    -1.20
    alers
    -1.20
     pagamento
    -1.19
    ⁩
    -1.18
    POSITIVE LOGITS
     иногда
    1.32
     Currently
    1.22
     Since
    1.22
    ;
    1.22
    ....
    1.22
     with
    1.21
    :+:
    1.20
    .......
    1.17
     in
    1.14
    .....
    1.14
    Activations Density 0.006%

    No Known Activations