© 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. 18416
    Prev
    Next
    INDEX
    Explanations

    location or address

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

    riddle, contrasts, states, actions, groups, purpose, requirements

    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
    かれる
    0.45
    Sund
    0.43
    מק
    0.43
    Opel
    0.42
    DU
    0.41
    ENV
    0.41
    াজী
    0.40
    ଧ
    0.40
    отно
    0.40
    Bonnie
    0.40
    POSITIVE LOGITS
     Contents
    0.47
     Sponge
    0.45
     euismod
    0.43
     যায়
    0.42
    étrica
    0.42
     bereit
    0.42
     Feuer
    0.41
     অভিব
    0.41
    angerschaft
    0.41
    ophores
    0.41
    Activations Density 0.000%

    No Known Activations