© 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. 15779
    Prev
    Next
    INDEX
    Explanations

    setting cell values

    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
     stijl
    -1.22
    ㈯
    -1.16
    indicated
    -1.13
    ícias
    -1.12
     盛り
    -1.12
     decoracion
    -1.10
     compagnies
    -1.10
     betere
    -1.09
    accident
    -1.08
    paket
    -1.07
    POSITIVE LOGITS
     of
    1.66
     from
    1.64
     about
    1.40
     (
    1.39
     by
    1.20
     with
    1.20
     to
    1.20
     such
    1.16
     so
    1.12
     two
    1.07
    Activations Density 0.010%

    No Known Activations