© 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. 71912
    Prev
    Next
    INDEX
    Explanations

    code snippets and structured text

    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
    Ă
    -1.37
     generell
    -1.30
    เพื่อ
    -1.30
     samme
    -1.23
     DIFFERENT
    -1.20
     DEFIN
    -1.17
     OTHER
    -1.16
     unbelievably
    -1.14
    internalType
    -1.11
    комо
    -1.11
    POSITIVE LOGITS
     its
    1.16
     should
    1.09
    Numéro
    1.06
     at
    1.04
     went
    1.03
     had
    1.02
     changed
    1.02
    얽
    0.99
    友人
    0.98
     venturing
    0.98
    Activations Density 0.002%

    No Known Activations