© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9567
    Prev
    Next
    INDEX
    Explanations

    code syntax and variable names

    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
     help
    -0.93
     dvě
    -0.89
     ones
    -0.88
     including
    -0.88
     adecuada
    -0.88
    ituary
    -0.84
     ऐसा
    -0.83
    WhereInput
    -0.83
     adecuado
    -0.82
    ykjav
    -0.82
    POSITIVE LOGITS
     formule
    1.06
     pemuda
    1.04
     batteri
    1.02
     bambu
    0.99
     piaci
    0.96
     Voilà
    0.96
     Série
    0.96
     ronde
    0.96
     plafon
    0.96
     benzin
    0.95
    Activations Density 0.003%

    No Known Activations