© 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. 33930
    Prev
    Next
    INDEX
    Explanations

    obtain data or copy

    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
     предостав
    -1.05
     being
    -1.04
    ribute
    -0.98
     born
    -0.95
     allowed
    -0.94
     тези
    -0.94
     enfermera
    -0.93
     was
    -0.88
     Pantai
    -0.88
     given
    -0.85
    POSITIVE LOGITS
     from
    2.03
     through
    1.30
    ઃ
    1.12
     rid
    1.06
     satisfactory
    1.05
     suitable
    1.03
     повіт
    1.03
     by
    1.03
     Obtain
    1.03
     sufficient
    1.02
    Activations Density 0.070%

    No Known Activations