© 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. 87688
    Prev
    Next
    INDEX
    Explanations

    information concerning

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

    widely accepted or common

    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
    炤
    0.54
    raš
    0.49
    谲
    0.47
    <unused84>
    0.46
    น
    0.46
    ేవ
    0.45
    แบ
    0.45
     섹
    0.45
    خرى
    0.45
    λάβ
    0.45
    POSITIVE LOGITS
     on
    0.56
     nobleman
    0.56
     with
    0.55
     died
    0.53
     stood
    0.53
     molecule
    0.53
     grating
    0.53
     as
    0.50
     stew
    0.49
     creature
    0.49
    Activations Density 0.000%

    No Known Activations