© 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. 129949
    Prev
    Next
    INDEX
    Explanations

    past locations

    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
    Entire
    -1.20
    през
    -1.07
     système
    -1.05
     Usuarios
    -1.05
     etme
    -1.04
    сль
    -1.04
     sokak
    -1.03
    缪
    -1.02
     tiden
    -1.02
    UNICIP
    -1.01
    POSITIVE LOGITS
     where
    2.45
     previously
    1.58
    where
    1.30
     formerly
    1.30
     Previously
    1.21
     ранее
    1.11
    Where
    1.11
     previous
    1.10
     où
    1.09
    formerly
    1.05
    Activations Density 0.042%

    No Known Activations