© 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. 38330
    Prev
    Next
    INDEX
    Explanations

    hope to avoid

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

    action verbs and following words

    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
    circa
    0.46
    内在
    0.45
    enson
    0.44
    гий
    0.42
    值为
    0.42
    骆
    0.42
    Hij
    0.42
    ла
    0.41
    시는
    0.41
    八
    0.41
    POSITIVE LOGITS
     benefit
    0.47
     tqdm
    0.44
     Ι
    0.44
     log
    0.44
     beneficio
    0.44
     mahi
    0.43
     OCEAN
    0.43
     refurb
    0.42
    মর
    0.42
     puddle
    0.42
    Activations Density 0.000%

    No Known Activations