© 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. 25982
    Prev
    Next
    INDEX
    Explanations

    psychoanalytic application and fox's

    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
    側から
    -1.13
     luscious
    -1.08
    vii
    -1.05
     seront
    -1.03
    punten
    -1.00
    ˇ
    -0.94
     ſen
    -0.94
     cél
    -0.93
    setPosition
    -0.92
     evocative
    -0.92
    POSITIVE LOGITS
     more
    1.15
     mildly
    1.14
    Embal
    1.13
     Probably
    1.11
     invigor
    1.09
     indicating
    1.08
     almost
    1.07
     only
    1.05
     prevents
    1.04
     arguably
    1.03
    Activations Density 0.000%

    No Known Activations