© 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. 156228
    Prev
    Next
    INDEX
    Explanations

    gas, refrigeration, collection

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

    lack of confidence

    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
     Pritchard
    0.53
     Lian
    0.50
     I
    0.49
     Pham
    0.48
    aka
    0.48
     Rachel
    0.47
    9
    0.47
    FF
    0.47
     Pru
    0.47
    anni
    0.47
    POSITIVE LOGITS
    ต
    0.52
     utilises
    0.49
    ט
    0.48
    टो
    0.47
    ร
    0.47
    रत
    0.47
    ล
    0.46
    ิตร
    0.46
    ن
    0.46
     silicate
    0.45
    Activations Density 0.000%

    No Known Activations