© 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. 68188
    Prev
    Next
    INDEX
    Explanations

    media attention and headlines

    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
     to
    -1.42
    A
    -1.09
    th
    -1.08
     you
    -1.02
    P
    -1.02
    J
    -0.98
    roring
    -0.96
     also
    -0.96
     urge
    -0.95
    go
    -0.95
    POSITIVE LOGITS
     headlines
    1.42
     attention
    1.34
    饽
    1.15
    獁
    1.13
     about
    1.13
    เกี่ยวกับ
    1.11
    ykjav
    1.10
     ympä
    1.09
     Architekt
    1.07
     interest
    1.05
    Activations Density 0.053%

    No Known Activations