© 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. 88005
    Prev
    Next
    INDEX
    Explanations

    knowing when

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

    monitoring trends

    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
    it
    0.48
    τία
    0.46
    вает
    0.45
    षि
    0.45
    ωσης
    0.45
     счета
    0.45
    ui
    0.45
    ?";
    0.45
    వులు
    0.44
     తీసుకు
    0.44
    POSITIVE LOGITS
     estrategias
    0.52
     null
    0.49
     täglich
    0.47
     opérateurs
    0.46
    เหนือ
    0.45
     isn
    0.45
     binnen
    0.43
     dirigeants
    0.43
    Bonjour
    0.42
     bescherm
    0.42
    Activations Density 0.000%

    No Known Activations