© 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. 194195
    Prev
    Next
    INDEX
    Explanations

    faith in me, Heroes of the Storm

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

    body size

    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
    ಾಮ
    0.50
    ᑎ
    0.48
    兒童
    0.47
    วัส
    0.47
    這是
    0.44
    ┄
    0.43
     pédicule
    0.43
     داستان
    0.43
    Ό
    0.42
    蘿
    0.42
    POSITIVE LOGITS
     Lifestyle
    0.55
     candidature
    0.54
     Healthcare
    0.52
     Mobility
    0.51
     Diageo
    0.49
     Higher
    0.48
     corporates
    0.47
     legitimate
    0.46
     livelihood
    0.46
     Correctional
    0.46
    Activations Density 0.000%

    No Known Activations