© 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. 113291
    Prev
    Next
    INDEX
    Explanations

    interrogative punctuation

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

    again or japanese

    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
    ニム
    0.47
     barons
    0.42
     escolh
    0.42
    rollen
    0.41
     screw
    0.41
    าม
    0.40
    :(
    0.40
     alber
    0.39
     barco
    0.39
     roky
    0.38
    POSITIVE LOGITS
    禎
    0.44
    再び
    0.42
     دوباره
    0.39
     সেখানকার
    0.38
     Closeup
    0.38
     وذلك
    0.37
     நவ
    0.37
     Plaza
    0.36
     مرکز
    0.36
    狯
    0.36
    Activations Density 0.101%

    No Known Activations