© 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. 4620
    Prev
    Next
    INDEX
    Explanations

    numbers and HTML tags

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

    options, rephrasing, rewrite, or variations

    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
     און
    0.28
     subjug
    0.27
     և
    0.26
     topLine
    0.25
     automl
    0.25
     moldings
    0.25
     prothorax
    0.25
     vực
    0.25
     goomba
    0.25
     ennemis
    0.25
    POSITIVE LOGITS
    1
    0.46
    4
    0.41
    <strong>
    0.40
    <h4>
    0.39
    <h3>
    0.38
    2
    0.38
    p
    0.38
    7
    0.37
    5
    0.36
    The
    0.36
    Activations Density 0.952%

    No Known Activations