© 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. 33705
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    -1.27
     sacerd
    -1.16
     there
    -1.07
    edade
    -1.04
     retirar
    -1.03
    ẅ
    -1.02
     glaubt
    -1.02
    denly
    -1.01
    性が
    -1.01
    Vay
    -1.00
    POSITIVE LOGITS
    -
    1.19
    %
    1.16
    !
    1.12
    obviously
    1.05
    //
    1.04
    "
    1.01
    ,
    1.01
    Launched
    0.97
    '
    0.97
     rencontre
    0.94
    Activations Density 0.288%

    No Known Activations