© 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. 190735
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    purpose or finding explanation

    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
     ชั้น
    0.45
    ชน์
    0.43
    '
    0.43
    ભાઇ
    0.42
    ोत्सव
    0.42
    жина
    0.42
     层
    0.42
    сування
    0.41
    ชั้น
    0.41
    媜
    0.41
    POSITIVE LOGITS
    EG
    0.45
     quaerat
    0.44
     Ksi
    0.42
     Jupyter
    0.41
     prostate
    0.41
     FSB
    0.40
     sitt
    0.40
     EGF
    0.40
     persistently
    0.40
     représentant
    0.39
    Activations Density 0.000%

    No Known Activations