© 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. 156727
    Prev
    Next
    INDEX
    Explanations

    sentence structures and descriptions

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

    pulsing lights

    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
     Där
    0.55
    !-
    0.51
    -
    0.50
    যাত্র
    0.48
    㕕
    0.47
     Drying
    0.47
    ！！
    0.46
     Bahnhof
    0.46
    !!
    0.45
    －
    0.45
    POSITIVE LOGITS
     respe
    0.45
    gue
    0.44
     abide
    0.42
     imbued
    0.42
    lewati
    0.41
     incorporar
    0.41
     entren
    0.41
    ಕ್
    0.40
    ᱠ
    0.40
    kipun
    0.40
    Activations Density 0.000%

    No Known Activations