© 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. 23514
    Prev
    Next
    INDEX
    Explanations

    listing examples after comma

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

    enumerated examples

    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
     일이
    0.44
     일을
    0.44
     Sail
    0.41
     얼
    0.41
     तालाब
    0.40
     একেবারেই
    0.40
     Cái
    0.40
    rig
    0.39
     บาง
    0.39
     cái
    0.39
    POSITIVE LOGITS
     país
    0.45
    囚
    0.45
     humanos
    0.44
     solidar
    0.43
     políticos
    0.42
     humanist
    0.42
     antrop
    0.42
     intim
    0.42
     generality
    0.42
     metaphors
    0.42
    Activations Density 0.000%

    No Known Activations