© 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. 42527
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    Scrum Master

    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
     스토리
    0.42
     인기
    0.42
    స్య
    0.41
    ؟!
    0.41
     workman
    0.40
     효
    0.39
     نرخ
    0.39
     Universität
    0.38
    '!
    0.38
    ’!
    0.38
    POSITIVE LOGITS
    those
    0.56
    Those
    0.55
    advertise
    0.51
    suma
    0.51
    text
    0.50
    tell
    0.49
    }$(
    0.49
    ket
    0.49
     हैव
    0.48
    infos
    0.48
    Activations Density 0.577%

    No Known Activations