© 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. 194556
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions

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

    conditions and use

    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
    queous
    0.49
    ا
    0.47
    priority
    0.45
    cre
    0.44
    sit
    0.44
    y
    0.44
    ું
    0.43
    dummies
    0.43
    ر
    0.43
    oxide
    0.42
    POSITIVE LOGITS
     podob
    0.64
     hemos
    0.58
     substit
    0.53
     biomark
    0.52
     замести
    0.51
     우리가
    0.50
     obnov
    0.50
     Stras
    0.49
     humankind
    0.49
     besonderen
    0.48
    Activations Density 0.000%

    No Known Activations