© 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. 25986
    Prev
    Next
    INDEX
    Explanations

    findings study results performed test designed

    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
    -1.15
    pendidikan
    -1.11
     where
    -1.08
    ̀nh
    -1.06
    astră
    -1.02
    ὑ
    -1.00
     картин
    -0.96
    ⽅
    -0.94
     maybe
    -0.94
     تواند
    -0.93
    POSITIVE LOGITS
    Needless
    1.22
    这些人
    1.04
     rêver
    1.04
     beschä
    1.04
     dessas
    1.02
     fournisseurs
    1.02
     uiteindelijk
    1.01
    velas
    1.01
     favoriser
    1.00
     этих
    0.99
    Activations Density 0.061%

    No Known Activations