© 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. 41812
    Prev
    Next
    INDEX
    Explanations

    Aust, Bundesliga, good

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

    arrange private babysitting

    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
     Governing
    0.48
     নিয়েই
    0.46
     Controls
    0.44
     geweld
    0.44
     張
    0.43
     assemblage
    0.42
     grime
    0.42
     電力
    0.41
    dylib
    0.41
    acles
    0.41
    POSITIVE LOGITS
    А
    0.55
     piloto
    0.49
    Aust
    0.49
    Ο
    0.48
    им
    0.47
    parrot
    0.46
    Schwe
    0.46
     kg
    0.45
    methoxy
    0.45
    א
    0.45
    Activations Density 0.000%

    No Known Activations