© 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. 55107
    Prev
    Next
    INDEX
    Explanations

    separate section, page rank, other threads

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

    other algorithms and concepts

    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
    ভ
    0.54
    که
    0.52
    ט
    0.52
    Гу
    0.49
    EVERY
    0.48
    ল
    0.48
    ਰ
    0.48
    INTRESOURCE
    0.47
    ગુ
    0.47
    레
    0.47
    POSITIVE LOGITS
    nade
    0.49
    sched
    0.47
     anderer
    0.46
     Andere
    0.44
    nych
    0.43
    ges
    0.42
    clides
    0.41
    nms
    0.41
     commons
    0.40
    nian
    0.40
    Activations Density 0.000%

    No Known Activations