© 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. 130906
    Prev
    Next
    INDEX
    Explanations

    action or state after "when"

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

    documentation and instructions

    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
    ま
    0.48
     Artin
    0.46
     Ispol
    0.45
    зм
    0.45
     istr
    0.44
    ब्रिट
    0.44
    たた
    0.43
    にと
    0.43
    izontally
    0.43
     &-
    0.42
    POSITIVE LOGITS
    ТС
    0.46
     लड़
    0.43
     göra
    0.42
    ága
    0.42
    িকের
    0.42
    ála
    0.42
     விநாயக
    0.41
    Filtered
    0.40
     পৌরসভার
    0.40
    ிறார்கள்
    0.40
    Activations Density 0.000%

    No Known Activations