© 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. 125900
    Prev
    Next
    INDEX
    Explanations

    forth in, acts or, meals is, next to, indicates no

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

    brackets and specific punctuation

    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
    ↵
    0.57
    reau
    0.48
    rière
    0.48
    ree
    0.47
    lege
    0.47
    ./
    0.46
    .!
    0.46
    ⚖
    0.44
    .??
    0.44
    AtPath
    0.44
    POSITIVE LOGITS
     tropomyosin
    0.53
     sông
    0.52
     inmun
    0.47
    ಲಿನ
    0.47
     ligands
    0.46
     demuestra
    0.46
     spline
    0.45
     expressway
    0.45
    டியில்
    0.44
     sepak
    0.44
    Activations Density 0.001%

    No Known Activations