© 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. 25459
    Prev
    Next
    INDEX
    Explanations

    awesome,

    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
     jika
    -1.22
     यदि
    -1.18
     शुर
    -1.14
    TimeoutException
    -1.14
     in
    -1.13
     \&
    -1.10
    textnormal
    -1.09
     Data
    -1.09
    EFIAPI
    -1.08
     In
    -1.06
    POSITIVE LOGITS
     limpar
    1.40
     poils
    1.35
     granat
    1.31
    みんな
    1.30
    Fuck
    1.30
     everything
    1.29
    Spesifikasi
    1.27
     uſ
    1.27
    全然
    1.25
     monstrous
    1.25
    Activations Density 0.020%

    No Known Activations