© 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. 131356
    Prev
    Next
    INDEX
    Explanations

    why or whereby

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

    without necessarily

    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
    맨
    0.50
    ０
    0.49
    前景
    0.48
    वते
    0.47
    IDO
    0.46
    ਜ਼
    0.45
    দৈ
    0.45
    idle
    0.44
    ヱ
    0.44
    packages
    0.43
    POSITIVE LOGITS
     waarom
    0.59
     wasn
    0.57
     waardoor
    0.54
     doesn
    0.53
     oddly
    0.52
     was
    0.50
     pourquoi
    0.50
     craziness
    0.49
     wodurch
    0.49
    色が
    0.48
    Activations Density 0.000%

    No Known Activations