© 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. 241615
    Prev
    Next
    INDEX
    Explanations

    numbers, cars, drives, girls

    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
    Concrete
    0.52
     ছয়
    0.50
    SOCK
    0.50
     нюан
    0.50
    🆕
    0.50
    𝟎
    0.50
     সংখ্যাল
    0.49
    oljš
    0.49
    🥩
    0.49
    <unused64>
    0.49
    POSITIVE LOGITS
     conferences
    0.54
     Gazi
    0.53
     conjunt
    0.52
    ==============]
    0.50
     lagoons
    0.48
     transient
    0.47
     mandi
    0.47
     vreme
    0.47
    ু
    0.46
     fart
    0.46
    Activations Density 0.000%

    No Known Activations