© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55163
    Prev
    Next
    INDEX
    Explanations

    the / a / an

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

    outside of certain contexts

    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
     마
    0.52
     Documentation
    0.49
     Boutique
    0.49
     Familie
    0.48
    getSimple
    0.47
     우선
    0.46
     문서
    0.44
    斐
    0.44
    Documentation
    0.44
     간단
    0.44
    POSITIVE LOGITS
     sexu
    0.45
     sexuales
    0.45
     novembro
    0.44
    ariam
    0.44
    á
    0.44
     determinada
    0.44
    ႅ
    0.42
     sexual
    0.42
     supone
    0.42
    apped
    0.41
    Activations Density 0.000%

    No Known Activations