© 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. 91949
    Prev
    Next
    INDEX
    Explanations

    finding research or making additions

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

    multivalue topics

    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
    the
    0.52
    на
    0.44
    <strong>
    0.42
    p
    0.42
    w
    0.42
    an
    0.42
    there
    0.41
    年
    0.41
     Glance
    0.41
     Heck
    0.40
    POSITIVE LOGITS
     ло
    0.63
     végétale
    0.55
     miał
    0.54
     gratuits
    0.54
     päev
    0.53
     двох
    0.52
     étaient
    0.51
     avaient
    0.50
     hadde
    0.49
     பாதுகாக்க
    0.49
    Activations Density 0.001%

    No Known Activations