© 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. 15487
    Prev
    Next
    INDEX
    Explanations

    Psychoanalytic or Chester Gladiators

    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
    gebras
    -1.15
    ()/
    -1.04
     perpé
    -1.03
    AddAttribute
    -1.01
     invertir
    -1.00
    +--
    -0.98
    ギュア
    -0.92
     jego
    -0.92
    NEZ
    -0.91
     døde
    -0.91
    POSITIVE LOGITS
     not
    1.53
     at
    1.10
     only
    1.09
     also
    1.09
    It
    1.05
    嚮
    0.93
     sowohl
    0.91
     from
    0.91
     it
    0.90
    When
    0.90
    Activations Density 0.000%

    No Known Activations