© 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. 41058
    Prev
    Next
    INDEX
    Explanations

    locket pendant

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

    distinguishing statements

    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
     합동
    0.50
    连续
    0.46
     coca
    0.45
    지
    0.43
    бами
    0.43
     ਇਕ
    0.43
    надцать
    0.43
    стива
    0.42
    小数
    0.42
    ভিন
    0.42
    POSITIVE LOGITS
    يمه
    0.49
    ย
    0.48
    roi
    0.47
    तरीय
    0.46
     tejto
    0.44
    whats
    0.44
    regarding
    0.44
    縝
    0.44
     herewith
    0.43
     ELLE
    0.43
    Activations Density 0.000%

    No Known Activations