© 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. 69067
    Prev
    Next
    INDEX
    Explanations

    financial and family terms

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

    examples and explanations with diverse 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
    DFLAGS
    0.49
     corresponds
    0.47
    CMAKE
    0.45
     samoz
    0.42
     conformations
    0.42
    さまざまな
    0.42
    Ⅽ
    0.42
    opens
    0.41
    documents
    0.41
     рассказывает
    0.41
    POSITIVE LOGITS
    ين
    0.54
    antina
    0.46
    Park
    0.41
    엑
    0.41
     Park
    0.40
    atil
    0.40
    ân
    0.39
     इसलिए
    0.39
    اشت
    0.39
     analisis
    0.39
    Activations Density 0.000%

    No Known Activations