© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 22227
    Prev
    Next
    INDEX
    Explanations

    api/device/lib/modal/blackberry

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

    code structure identifiers

    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
    θεση
    0.26
    录
    0.24
    JSON
    0.23
     année
    0.23
     αρχ
    0.23
    开源
    0.23
     estánd
    0.22
    étrica
    0.22
     değişiklik
    0.22
    漲
    0.22
    POSITIVE LOGITS
    そのため
    0.23
    මුත්
    0.22
     ልዩ
    0.21
    をご確認
    0.20
    ewe
    0.20
    }=$
    0.20
     ได้
    0.20
     عزيز
    0.20
    esha
    0.20
    exceptional
    0.20
    Activations Density 0.000%

    No Known Activations