© 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. 39243
    Prev
    Next
    INDEX
    Explanations

    let mathematical declarations

    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
    deserved
    -1.08
    glicher
    -1.05
    去了
    -1.04
    苼
    -1.01
    photograph
    -1.01
    [{\
    -1.00
    asje
    -1.00
    馊
    -0.99
     komment
    -0.98
    eably
    -0.96
    POSITIVE LOGITS
     também
    1.24
     its
    1.17
     también
    1.16
     a
    1.16
     with
    1.09
     też
    1.06
     his
    1.05
     also
    1.02
    ческих
    1.00
    also
    0.98
    Activations Density 0.043%

    No Known Activations