© 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. 28547
    Prev
    Next
    INDEX
    Explanations

    place names

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

    after showering

    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
    lym
    0.46
    tiny
    0.46
    ा
    0.44
    äl
    0.44
     Copy
    0.44
    細胞
    0.43
    。.
    0.43
    õ
    0.43
    一份
    0.42
    ១
    0.42
    POSITIVE LOGITS
     apprent
    0.53
     slag
    0.52
     نیوز
    0.49
     Colombie
    0.49
     ancien
    0.49
     QC
    0.48
     சட்ட
    0.48
     irland
    0.48
     gout
    0.47
     шла
    0.47
    Activations Density 0.001%

    No Known Activations