© 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. 135468
    Prev
    Next
    INDEX
    Explanations

    standard equipment

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

    bad internet

    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
    🌭
    0.50
    旖
    0.49
    ır
    0.49
    🍝
    0.48
    거나
    0.47
    𝚍
    0.47
     भीड़
    0.47
    🍟
    0.47
    ında
    0.46
     после
    0.46
    POSITIVE LOGITS
     constructs
    0.46
     engagements
    0.45
    ;
    0.44
     ejercer
    0.43
     aggrieved
    0.43
     performers
    0.43
     conduits
    0.42
     bearers
    0.42
    elom
    0.42
     belts
    0.42
    Activations Density 0.001%

    No Known Activations