© 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. 11261
    Prev
    Next
    INDEX
    Explanations

    rate at or of

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

    rate at or of

    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
    محمد
    0.46
    Ironically
    0.44
     (
    0.42
     empirically
    0.41
    ຫລ
    0.40
     experimentally
    0.40
    EXPERIMENTAL
    0.40
    },
    0.39
    electron
    0.38
    مكن
    0.38
    POSITIVE LOGITS
    咱
    0.48
     différen
    0.47
     mūsų
    0.46
     આપણા
    0.45
     적용
    0.45
     troviamo
    0.44
     föränd
    0.44
     terjadinya
    0.44
    뻗
    0.44
    asjon
    0.44
    Activations Density 0.000%

    No Known Activations