© 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. 203186
    Prev
    Next
    INDEX
    Explanations

    images and other media

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

    government regulations content

    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
     ABSORBED
    0.52
    兼用
    0.52
    7
    0.51
    ?:
    0.50
    +,
    0.50
    6
    0.50
    <unused1799>
    0.49
    ?,
    0.49
    鰯
    0.49
    +.
    0.48
    POSITIVE LOGITS
    gence
    0.48
     गोरखपुर
    0.46
    ngthen
    0.44
    迟
    0.44
    giene
    0.41
    سن
    0.41
    ৎস্য
    0.41
     Suspension
    0.40
    Emitter
    0.39
     झूठ
    0.39
    Activations Density 0.000%

    No Known Activations