© 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. 76865
    Prev
    Next
    INDEX
    Explanations

    planning an event

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

    lawyer told, training in, brain circuit

    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
    ন্যায়
    0.44
    ismillahirrah
    0.42
    Deprecated
    0.40
    븅
    0.39
     নিয়ম
    0.39
    Референ
    0.38
    icator
    0.38
    педия
    0.38
    ഐ
    0.38
     Slav
    0.38
    POSITIVE LOGITS
    i
    0.53
    an
    0.52
    t
    0.50
    ké
    0.49
     CaO
    0.49
     Pullman
    0.48
     Grandes
    0.47
    qui
    0.46
    bedarf
    0.46
    tia
    0.46
    Activations Density 0.002%

    No Known Activations