© 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. 64402
    Prev
    Next
    INDEX
    Explanations

    following report

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

    bone density

    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
     syntactic
    0.51
    𝑤
    0.47
     نوع
    0.47
     synth
    0.45
    Tian
    0.45
     طلعت
    0.45
    Dias
    0.45
     synthetic
    0.44
    新的
    0.44
     aspart
    0.44
    POSITIVE LOGITS
    致します
    0.48
    ক্র
    0.47
    ீ
    0.45
    nj
    0.45
    amas
    0.43
    allowSlide
    0.43
    imą
    0.42
    ロッ
    0.42
    rs
    0.41
    犹如
    0.41
    Activations Density 0.000%

    No Known Activations