© 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. 203117
    Prev
    Next
    INDEX
    Explanations

    multi-language usage

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

    individual responses

    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
     uplift
    0.49
    衡
    0.45
     remed
    0.44
    \/}
    0.44
     chuck
    0.43
     flank
    0.42
     smoot
    0.42
     betterment
    0.42
    สด
    0.41
    เพิ่ม
    0.40
    POSITIVE LOGITS
    წი
    0.50
    exemple
    0.49
     বক্তব
    0.47
    εν
    0.46
    سوال
    0.46
    ዠ
    0.46
    operateur
    0.45
    ẩy
    0.45
    ibilidades
    0.45
    ⵃ
    0.45
    Activations Density 0.000%

    No Known Activations