© 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. 174456
    Prev
    Next
    INDEX
    Explanations

    list context and enumeration

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

    API, IDs, code terms

    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
     Procter
    0.46
    였
    0.43
     Nokia
    0.42
     CNN
    0.41
     Morocco
    0.41
    Autoresizing
    0.40
     was
    0.40
     Unilever
    0.40
     Merck
    0.40
     somewhere
    0.40
    POSITIVE LOGITS
    🎓
    0.47
    扩展
    0.47
     समझेंगे
    0.46
    Arquivo
    0.46
    令和
    0.46
    Quanto
    0.45
    zees
    0.45
    íb
    0.44
     참고
    0.44
    detalle
    0.44
    Activations Density 0.003%

    No Known Activations