© 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. 15287
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

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

    harder, impossible, incentive

    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
    يمكن
    0.49
    ]#
    0.49
    <0xBB>
    0.47
    ient
    0.46
     écrit
    0.46
    தமிழ
    0.46
    parametric
    0.44
    analysis
    0.44
    ডিস
    0.44
    ‐
    0.44
    POSITIVE LOGITS
     напа
    0.46
     thuyền
    0.43
     ску
    0.42
     προσωπ
    0.42
     गुन्हा
    0.42
     спа
    0.41
     женщина
    0.41
     माणसा
    0.41
     moglie
    0.41
     мировой
    0.41
    Activations Density 0.000%

    No Known Activations