© 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. 104376
    Prev
    Next
    INDEX
    Explanations

    admiration and fans

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

    fan of

    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
    el
    0.68
    К
    0.66
    past
    0.63
    yas
    0.62
    У
    0.61
    nar
    0.59
    ில்
    0.59
    les
    0.58
    ną
    0.57
    calf
    0.57
    POSITIVE LOGITS
     fan
    0.76
    粉絲
    0.72
     Fan
    0.67
     फैन
    0.64
    扇
    0.62
    粉丝
    0.59
    ファン
    0.57
    Fan
    0.57
    팬
    0.57
     fans
    0.56
    Activations Density 0.027%

    No Known Activations