© 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. 73218
    Prev
    Next
    INDEX
    Explanations

    words in sequences

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

    naming suggestions

    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
    s
    0.62
    </i>
    0.51
    sm
    0.50
     divulg
    0.50
    signup
    0.45
    賃
    0.44
    sto
    0.42
    spe
    0.41
     modo
    0.41
     البسط
    0.41
    POSITIVE LOGITS
     উপভোগ
    0.52
     arched
    0.48
    కాలు
    0.47
    大部分
    0.46
    ကာ
    0.45
    ዳ
    0.45
    atief
    0.45
     ಸಾಮಾನ್ಯವಾಗಿ
    0.45
    শকা
    0.44
    小さい
    0.44
    Activations Density 0.001%

    No Known Activations