© 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. 193241
    Prev
    Next
    INDEX
    Explanations

    love and somebody

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

    current condition

    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
     çıktı
    0.54
    ಬೇ
    0.54
     பெரும்பாலான
    0.53
     นิ
    0.51
    𝒞
    0.50
    !।
    0.49
    ಕ್ಕಾಗಿ
    0.48
     പോലുള്ള
    0.48
    мас
    0.47
    𝚢
    0.47
    POSITIVE LOGITS
    ↵
    0.55
     refrain
    0.50
    ).
    0.46
     up
    0.44
    ify
    0.44
    フ
    0.43
     refrained
    0.43
     preoccupation
    0.42
    );
    0.42
     U
    0.42
    Activations Density 0.000%

    No Known Activations