© 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. 132682
    Prev
    Next
    INDEX
    Explanations

    relationship, partner, request, fight, modulation, appointed

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

    medical, financial, or technical contexts

    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
    刳
    0.49
     کہتے
    0.47
    格局
    0.45
    适应
    0.45
     없고
    0.44
     transcendence
    0.43
     एकता
    0.43
     دستگاه
    0.43
     фундамента
    0.43
    elled
    0.42
    POSITIVE LOGITS
     onus
    0.46
    寐
    0.46
    wohner
    0.44
     jeweil
    0.44
    mbh
    0.43
     rebord
    0.42
    ENGINE
    0.42
     sommige
    0.42
    }([
    0.41
    CUSTOM
    0.41
    Activations Density 0.000%

    No Known Activations