© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104879
    Prev
    Next
    INDEX
    Explanations

    your wheat delegates cover

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

    kg loss of pay

    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
    灿
    0.46
    受け
    0.43
     ക
    0.42
    韬
    0.42
     değil
    0.42
     раді
    0.42
    ക
    0.42
     receiving
    0.41
    ারে
    0.41
    鎸
    0.41
    POSITIVE LOGITS
     MO
    0.41
    Comp
    0.40
     shabby
    0.40
    (−
    0.40
    clo
    0.40
    "},{"
    0.40
    relax
    0.40
    نسان
    0.39
     anno
    0.39
    {-\
    0.39
    Activations Density 0.001%

    No Known Activations