© 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. 126840
    Prev
    Next
    INDEX
    Explanations

    Save settings, click or archive

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

    doing something interesting

    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
    na
    0.50
    entities
    0.50
    chelle
    0.48
    hell
    0.45
    char
    0.44
    att
    0.44
     सेक
    0.44
    栋
    0.43
    ca
    0.43
    dos
    0.43
    POSITIVE LOGITS
     הו
    0.46
    🥬
    0.46
     ня
    0.46
    ки
    0.46
     sobri
    0.45
     bếp
    0.45
    ㎞
    0.45
    וריה
    0.44
    礽
    0.44
    fNil
    0.44
    Activations Density 0.000%

    No Known Activations