© 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. 245372
    Prev
    Next
    INDEX
    Explanations

    starting journeys and filming

    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
    芃
    0.46
    失
    0.46
    他
    0.46
    以内
    0.45
    持
    0.45
    これらの
    0.45
    在
    0.44
    在她
    0.44
    以
    0.44
    ႏ
    0.44
    POSITIVE LOGITS
     tertentu
    0.49
     pedro
    0.43
    .
    0.43
     taping
    0.42
     transfers
    0.42
     recordings
    0.42
    </h3>
    0.41
     doorway
    0.41
    omia
    0.41
     planing
    0.41
    Activations Density 0.000%

    No Known Activations