© 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. 212464
    Prev
    Next
    INDEX
    Explanations

    followed by noun/phrase

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

    shapes, geom, operate, taps, cracking, sharing

    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
    áš
    0.47
    詆
    0.44
     প্রবাহিত
    0.44
     вкус
    0.44
     ඔහුගේ
    0.44
     murderous
    0.42
    ຈ
    0.42
     اعزائي
    0.41
     ক্যান্স
    0.41
     PUBLIC
    0.41
    POSITIVE LOGITS
    Eagle
    0.47
    っきり
    0.46
     freg
    0.45
     bibliographic
    0.45
    先に
    0.45
     case
    0.45
     COMEN
    0.45
     Narayan
    0.43
    剪
    0.43
    ந்திரன்
    0.42
    Activations Density 0.000%

    No Known Activations