© 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. 38366
    Prev
    Next
    INDEX
    Explanations

    `for one` / `next step`

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

    explanations:

    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
    חה
    0.51
    ן
    0.50
    kannya
    0.48
    iline
    0.47
    婚
    0.46
    訟
    0.46
    чний
    0.46
     Lux
    0.46
    ▥
    0.46
     हेड
    0.45
    POSITIVE LOGITS
    f
    0.48
     সম্পর্
    0.45
    zero
    0.45
     dian
    0.44
    derm
    0.44
     fác
    0.44
    rein
    0.44
    improve
    0.43
    median
    0.43
    circular
    0.42
    Activations Density 0.000%

    No Known Activations