© 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. 39068
    Prev
    Next
    INDEX
    Explanations

    code identifiers, variable names, module names

    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
     in
    -1.30
     first
    -1.22
     only
    -1.18
     with
    -1.07
     started
    -1.00
     essentially
    -0.99
     people
    -0.96
     practically
    -0.94
     may
    -0.94
     using
    -0.93
    POSITIVE LOGITS
     poches
    1.19
    –
    1.17
    诬
    1.17
     verdaderas
    1.15
    帰って
    1.13
     trám
    1.13
     poderosos
    1.13
    dő
    1.13
     pêche
    1.11
     tratamientos
    1.11
    Activations Density 0.055%

    No Known Activations