© 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. 34038
    Prev
    Next
    INDEX
    Explanations

    Northern side, July, controls

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

    verifies, seen, dramatic, Him

    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
     ft
    0.49
     +
    0.49
     of
    0.48
    apixel
    0.46
    Antib
    0.46
    ों
    0.45
     dva
    0.45
    angk
    0.44
    Diagonal
    0.43
     कीमत
    0.43
    POSITIVE LOGITS
     ベージュ
    0.57
    𝙮
    0.53
    ORGE
    0.47
     cursing
    0.47
     آ
    0.47
     vigorously
    0.46
     intensely
    0.46
     guaranteeing
    0.46
     extraordinarily
    0.45
     assuring
    0.45
    Activations Density 0.000%

    No Known Activations