© 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. 5389
    Prev
    Next
    INDEX
    Explanations

    entering something

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

    requests and answers

    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
    दो
    0.38
    গুলিতে
    0.37
    ҷ
    0.37
     सिंहासन
    0.37
    형
    0.36
    오늘
    0.36
    Literatura
    0.36
    अच्छा
    0.35
    ō
    0.35
    জ্
    0.35
    POSITIVE LOGITS
     xref
    0.46
     outsiders
    0.46
     entrants
    0.45
     outsider
    0.44
     entrant
    0.44
     acceder
    0.44
     memasuki
    0.43
     thăm
    0.42
     entering
    0.42
     নিজেও
    0.42
    Activations Density 0.030%

    No Known Activations