© 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. 156500
    Prev
    Next
    INDEX
    Explanations

    My Hero Academia, accident or

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

    analyzing and developing states

    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
    orini
    0.57
    aksanaan
    0.54
    typen
    0.53
    dte
    0.52
    я
    0.52
    u
    0.52
    during
    0.51
     luminos
    0.50
    க்ஸ
    0.50
    p
    0.50
    POSITIVE LOGITS
     SUR
    0.54
     Camb
    0.52
     hydrolyzed
    0.50
     Canyon
    0.46
     Assault
    0.46
     Air
    0.46
     Brah
    0.45
    خرج
    0.45
     commercial
    0.45
     canyon
    0.44
    Activations Density 0.001%

    No Known Activations