© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    additional2. timing3. permanent4. best5. prospec

    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
    cerita
    -0.86
     kull
    -0.84
     ditangkap
    -0.83
    Lager
    -0.82
     accol
    -0.79
     alberg
    -0.77
     fabrique
    -0.77
     egg
    -0.77
    lasse
    -0.76
    ERSHIP
    -0.76
    POSITIVE LOGITS
     attempt
    0.99
     attempted
    0.97
    ENTER
    0.86
    𝙴
    0.81
     try
    0.80
     kvůli
    0.79
     expected
    0.78
    Ris
    0.77
     args
    0.76
    tio
    0.75
    Activations Density 0.126%

    No Known Activations