© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32950
    Prev
    Next
    INDEX
    Explanations

    eigenvalues and eigenfunctions

    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
     and
    -1.51
     or
    -1.23
     their
    -1.16
    —
    -1.05
    ;
    -1.04
     மற்றும்
    -1.00
    :
    -0.99
    PREPARATION
    -0.94
     Greater
    -0.92
     озеро
    -0.92
    POSITIVE LOGITS
     ſtre
    1.29
    lné
    1.23
     tragé
    1.08
     demonio
    1.08
     薬局
    1.07
     crê
    1.06
    vaila
    1.05
     Când
    1.05
     diventato
    1.05
     ZEALAND
    1.03
    Activations Density 0.085%

    No Known Activations