© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    recent topics and changes

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

    importance or likelihood

    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
    <b>
    0.46
    ’.
    0.45
    ur
    0.40
     &
    0.39
    aver
    0.39
    '.
    0.39
    ?.
    0.39
    ；
    0.38
    .*
    0.38
    ¹.
    0.38
    POSITIVE LOGITS
     ahorita
    0.71
     сейчас
    0.66
     lately
    0.64
     этом
    0.63
     этого
    0.63
     요즘
    0.63
     tutaj
    0.60
     هذا
    0.59
     sekarang
    0.59
     này
    0.59
    Activations Density 0.089%

    No Known Activations