© 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. 34-GEMMASCOPE-RES-131K
    7. 106580
    Prev
    Next
    INDEX
    Explanations

    Android resource identifiers

    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_34/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
     that
    -1.48
    inerario
    -1.23
     what
    -1.16
    !!
    -1.02
    !
    -0.98
    What
    -0.97
    وائ
    -0.95
    应当
    -0.94
     this
    -0.91
     one
    -0.91
    POSITIVE LOGITS
     AUSSI
    1.07
    gypte
    1.05
     Créez
    1.04
    OKAY
    1.02
    ကိုးကား
    1.02
    ské
    1.01
    BEAUTY
    0.99
    CIV
    0.98
     elektrische
    0.98
    hadapi
    0.98
    Activations Density 0.004%

    No Known Activations