© 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. 61329
    Prev
    Next
    INDEX
    Explanations

    implied warranties

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

    implied conditions and warranty

    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
     τ
    0.57
    <0xAB>
    0.54
    a
    0.51
     a
    0.50
     δ
    0.50
    л
    0.49
    etermined
    0.48
     Y
    0.48
    ie
    0.47
     aiding
    0.47
    POSITIVE LOGITS
    Deadline
    0.48
     Existem
    0.48
     gleichen
    0.47
    تھی
    0.46
    Золо
    0.46
     الحد
    0.45
    EDGE
    0.45
     bahawa
    0.45
    Cookies
    0.44
    باب
    0.44
    Activations Density 0.001%

    No Known Activations