© 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. 98192
    Prev
    Next
    INDEX
    Explanations

    art gallery, their knowledge, your options

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

    aggregated, anonymized

    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
    ર્સ
    0.44
    PHEN
    0.44
    Shortcut
    0.42
    VEST
    0.42
    утбу
    0.42
    ));
    0.41
    Tropical
    0.40
    ),(
    0.40
     ayrıca
    0.40
    庻
    0.40
    POSITIVE LOGITS
    ido
    0.55
    ris
    0.54
    在你
    0.50
    aina
    0.49
    watts
    0.49
    ovo
    0.48
    inta
    0.48
    ovaž
    0.47
     लीक
    0.47
    iodo
    0.46
    Activations Density 0.002%

    No Known Activations