© 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. 193636
    Prev
    Next
    INDEX
    Explanations

    location and states

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

    describing states and qualities

    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
    ustainability
    0.49
    де
    0.47
    ukun
    0.46
    ⏸
    0.46
    Estos
    0.45
     அடுத்து
    0.45
    ⏭
    0.45
    وكان
    0.44
    Powerful
    0.44
    洴
    0.44
    POSITIVE LOGITS
     gimmick
    0.62
     erythematosus
    0.54
     smear
    0.50
     larva
    0.50
     flawless
    0.49
     cleft
    0.49
     torment
    0.48
     brownish
    0.48
     very
    0.48
     nicknamed
    0.48
    Activations Density 0.000%

    No Known Activations