© 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. 110603
    Prev
    Next
    INDEX
    Explanations

    ex-partners, payment, authority, failing

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

    leaves and communication

    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
     डब्ल्यू
    0.49
     Laughlin
    0.48
     δο
    0.47
    tting
    0.46
     ARR
    0.45
     Puzzle
    0.45
    瞠
    0.42
    पात
    0.42
     puzzles
    0.42
    㡀
    0.41
    POSITIVE LOGITS
    ニム
    0.47
     بلوچ
    0.46
    Revenue
    0.44
     misplaced
    0.44
     राजस्व
    0.44
     entrevist
    0.43
     présentée
    0.43
     snake
    0.43
    ക്കാര
    0.43
     presentaron
    0.43
    Activations Density 0.001%

    No Known Activations