© 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. 106885
    Prev
    Next
    INDEX
    Explanations

    "full", "multiple", "playlists", "reach"

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

    against punctuation

    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
    چ
    0.49
    ovich
    0.45
    所属
    0.44
    ین
    0.44
    у
    0.44
    地元
    0.43
     bekend
    0.43
     athe
    0.41
     harmonic
    0.41
     athletic
    0.41
    POSITIVE LOGITS
    Mt
    0.48
    immobil
    0.48
    柺
    0.47
    kina
    0.46
    Plastic
    0.46
    舢
    0.46
    hiro
    0.46
    neither
    0.46
     lésions
    0.46
    InCM
    0.45
    Activations Density 0.000%

    No Known Activations