© 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. 73240
    Prev
    Next
    INDEX
    Explanations

    can or is it possible to

    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
    Either
    -1.20
     poderão
    -1.16
    »;
    -1.12
    räck
    -1.10
     deverá
    -1.08
     acte
    -1.08
     necessárias
    -1.08
    attività
    -1.07
     terão
    -1.05
     unut
    -1.03
    POSITIVE LOGITS
     without
    1.71
     be
    1.43
     still
    1.36
     there
    1.34
     this
    1.28
     do
    1.23
     with
    1.20
     if
    1.20
     get
    1.13
     Without
    1.13
    Activations Density 0.116%

    No Known Activations