© 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. 58342
    Prev
    Next
    INDEX
    Explanations

    Board code witnesses

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

    emphasis or placeholders

    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
     agarr
    0.61
     படங்களில்
    0.56
     ミニ
    0.53
     интегри
    0.52
    庠
    0.52
    ่ง
    0.52
     batang
    0.50
     Parab
    0.50
    酲
    0.48
     BEGIN
    0.48
    POSITIVE LOGITS
    lu
    0.51
    Arithmetic
    0.48
    tit
    0.46
    oz
    0.44
    dst
    0.43
    dl
    0.43
    an
    0.43
    sigma
    0.43
    dometer
    0.43
    Per
    0.42
    Activations Density 0.000%

    No Known Activations