© 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. 65860
    Prev
    Next
    INDEX
    Explanations

    dialing, matter, high

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

    multilingual technical concepts

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.43
     написал
    0.41
     assigns
    0.41
     wrote
    0.41
     unin
    0.41
     |.
    0.40
    inuation
    0.40
     +.
    0.39
     emailing
    0.38
     -$
    0.38
    POSITIVE LOGITS
     déchir
    0.49
     জমে
    0.47
    🍭
    0.44
     éduc
    0.43
    逐渐
    0.42
    因为它
    0.42
     정확
    0.42
     විශේෂ
    0.42
    avoir
    0.41
    ඳ
    0.41
    Activations Density 0.001%

    No Known Activations