© 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. 78731
    Prev
    Next
    INDEX
    Explanations

    specific following words

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

    structured lists and stages

    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
     inadmissible
    0.50
     いたし
    0.50
    كس
    0.49
    յան
    0.49
    ա
    0.45
     قلت
    0.45
     いく
    0.45
    мун
    0.45
     沒有
    0.44
    පත්
    0.44
    POSITIVE LOGITS
    S
    0.52
    US
    0.50
    Review
    0.49
    日本の
    0.48
    ES
    0.48
    5
    0.46
    0
    0.45
     REVIEW
    0.45
    HY
    0.45
    世界
    0.44
    Activations Density 0.000%

    No Known Activations