© 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. 41203
    Prev
    Next
    INDEX
    Explanations

    screenshots and technical descriptions

    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
    siniz
    0.45
    द्रोह
    0.44
    颀
    0.44
     Forecasting
    0.42
     mengatakan
    0.42
     khawatir
    0.41
    可以说
    0.40
    überküloz
    0.40
    წიფ
    0.40
    \}=
    0.40
    POSITIVE LOGITS
     enhancements
    0.43
     renter
    0.43
     cumpr
    0.42
     служит
    0.42
     enhancement
    0.42
     overhaul
    0.42
    物
    0.41
     aft
    0.41
     تأثير
    0.41
     automático
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.