© 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. 196465
    Prev
    Next
    INDEX
    Explanations

    grit your, until a, often one

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

    code syntax with angle brackets

    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
    ူ
    0.45
    ]$-
    0.45
     disposit
    0.44
    INATION
    0.43
     breeder
    0.43
     partnering
    0.41
    :
    0.41
    ]-
    0.41
     dissection
    0.40
     lại
    0.40
    POSITIVE LOGITS
    耺
    0.61
     intérieur
    0.54
     زائدا
    0.53
    ബ
    0.52
     automatiquement
    0.51
     የስ
    0.51
     কপ
    0.49
     Soder
    0.48
     пробе
    0.45
     الساعة
    0.45
    Activations Density 0.001%

    No Known Activations