© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201947
    Prev
    Next
    INDEX
    Explanations

    who is the author

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ar
    0.54
     j
    0.52
     $\
    0.48
     π
    0.46
     ин
    0.46
     z
    0.45
     следу
    0.45
     tzv
    0.45
     Mediterr
    0.44
     II
    0.44
    POSITIVE LOGITS
    데
    0.52
    מק
    0.48
    обс
    0.47
    ရင်း
    0.46
     tremendously
    0.46
    僳
    0.45
    Dogs
    0.45
    很是
    0.44
    橋
    0.44
    مانی
    0.44
    Activations Density 0.000%

    No Known Activations