© 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. 115703
    Prev
    Next
    INDEX
    Explanations

    editing services

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

    technical terms and code snippets

    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
    淈
    0.47
    VOLUME
    0.46
     e
    0.45
    MARK
    0.45
    接受
    0.44
     explore
    0.43
    探
    0.43
     accep
    0.43
    ENCE
    0.43
     accept
    0.43
    POSITIVE LOGITS
    ם
    0.56
    ן
    0.54
     הער
    0.52
     sorgt
    0.50
    何度も
    0.49
    טית
    0.47
     シュ
    0.47
    кологи
    0.47
    sz
    0.46
    스럽
    0.46
    Activations Density 0.000%

    No Known Activations