© 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. 113210
    Prev
    Next
    INDEX
    Explanations

    average or conditional

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

    occur with words like "this is"

    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
    V
    0.59
     deix
    0.54
    G
    0.53
    Gr
    0.50
     delle
    0.50
    C
    0.50
    N
    0.50
    Con
    0.49
     proponent
    0.49
    MAN
    0.48
    POSITIVE LOGITS
    azität
    0.48
    сіння
    0.47
    atação
    0.45
     قطعة
    0.44
     أغ
    0.44
     평균
    0.43
    putString
    0.43
    itação
    0.43
    鲑
    0.43
    imit
    0.42
    Activations Density 0.000%

    No Known Activations