© 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. 159016
    Prev
    Next
    INDEX
    Explanations

    helping `Rod` celebrate

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

    technical labels or definitions

    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
    ेयर
    0.47
     onboarding
    0.47
    बत
    0.46
    ApiCalls
    0.46
     выполнять
    0.46
     देखील
    0.46
    ⓵
    0.45
    Video
    0.45
    หลัง
    0.45
     останов
    0.45
    POSITIVE LOGITS
     xml
    0.50
     zna
    0.47
    了解到
    0.45
     examine
    0.44
     recherche
    0.44
    xml
    0.42
    }$\
    0.42
     enkele
    0.42
    werken
    0.41
     lahko
    0.40
    Activations Density 0.000%

    No Known Activations