© 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. 109280
    Prev
    Next
    INDEX
    Explanations

    questions, availability, and states of being

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

    animals, men, evolving, element, relays

    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
    inoj
    0.52
    au
    0.48
    is
    0.46
    as
    0.45
    Rüyada
    0.45
    人气
    0.43
    ximately
    0.41
    ཡ
    0.41
    adi
    0.41
    ahana
    0.40
    POSITIVE LOGITS
     szá
    0.54
     estadística
    0.53
     Pá
    0.51
     sende
    0.49
     és
    0.48
    Celltype
    0.47
    솝
    0.47
     hogares
    0.47
     adsor
    0.47
    ستان
    0.46
    Activations Density 0.001%

    No Known Activations