© 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. 182071
    Prev
    Next
    INDEX
    Explanations

    application and OS terms

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

    application and system components

    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
     modificar
    0.49
     കാരണ
    0.47
     reforzar
    0.46
    ដើម្បី
    0.46
    }}.
    0.46
     הי
    0.45
    hofer
    0.45
    রামর্শ
    0.44
    mediately
    0.43
     আসল
    0.43
    POSITIVE LOGITS
    application
    0.45
    Alle
    0.45
    Os
    0.44
    Denne
    0.43
    Esta
    0.42
    М
    0.42
    Osm
    0.42
    Application
    0.42
    d
    0.42
    Dieser
    0.42
    Activations Density 0.001%

    No Known Activations