© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200895
    Prev
    Next
    INDEX
    Explanations

    voluntary data provision

    np_acts-logits-general · gemini-2.5-flash-lite

    oldest, often, continue, IE, barric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    úa
    0.44
    ucin
    0.42
    ，
    0.40
    ą
    0.40
    ę
    0.40
     pueblo
    0.40
     repaired
    0.40
    }.}
    0.40
    Avro
    0.40
     cleansed
    0.39
    POSITIVE LOGITS
     negatif
    0.52
    혹
    0.49
     sku
    0.48
     CRA
    0.47
     Oko
    0.47
    you
    0.47
     nedir
    0.46
    tre
    0.46
     Identifier
    0.46
     identifik
    0.46
    Activations Density 0.000%

    No Known Activations