© 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. 204133
    Prev
    Next
    INDEX
    Explanations

    sale service

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

    water, health, or code assumptions

    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
    Entities
    0.52
    ponential
    0.50
    Conformance
    0.49
    渽
    0.46
    getElement
    0.45
    Datasets
    0.45
    Competitive
    0.44
    Attachments
    0.44
    蚓
    0.44
     densité
    0.44
    POSITIVE LOGITS
     Fuller
    0.45
    縷
    0.42
    bath
    0.41
    はり
    0.41
     Dunne
    0.40
    fulfilled
    0.39
    細菌
    0.39
     аутох
    0.38
     сложи
    0.38
    www
    0.37
    Activations Density 0.001%

    No Known Activations