© 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. 219799
    Prev
    Next
    INDEX
    Explanations

    stocks or assets

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

    parenthetical and contrasting statements

    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
     CharPtr
    0.54
     entste
    0.52
     nCmd
    0.51
    രുത്
    0.47
     tropomyosin
    0.46
    nCurr
    0.45
    kN
    0.45
    脂
    0.45
    ныгы
    0.44
    ны
    0.44
    POSITIVE LOGITS
    스로
    0.46
    사의
    0.46
    사가
    0.45
    밴
    0.45
    먼
    0.44
    anny
    0.44
    처럼
    0.43
    -
    0.42
     앞에
    0.41
    Sher
    0.41
    Activations Density 0.000%

    No Known Activations