© 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. 237242
    Prev
    Next
    INDEX
    Explanations

    all educational / British Racing

    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
    var
    0.52
    $.
    0.52
     bait
    0.50
     collector
    0.48
    rio
    0.47
     saab
    0.47
     min
    0.46
     backend
    0.46
     but
    0.45
     hassle
    0.45
    POSITIVE LOGITS
    تك
    0.52
    ინგ
    0.52
    დ
    0.51
    크
    0.51
    다고
    0.50
    ტ
    0.49
    틋
    0.48
    კ
    0.48
    훈련
    0.48
    ſe
    0.47
    Activations Density 0.001%

    No Known Activations