© 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. 243341
    Prev
    Next
    INDEX
    Explanations

    service status information

    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
    साम
    0.46
     आत्मनिर्भर
    0.44
    <0xD0>
    0.44
    ेंट
    0.42
     Produkt
    0.42
     తాజాగా
    0.42
    दय
    0.41
     CALIFORNIA
    0.41
     तपाई
    0.41
    ]==
    0.41
    POSITIVE LOGITS
     hostel
    0.52
    dates
    0.51
    status
    0.50
     圆
    0.45
    king
    0.45
    format
    0.44
     format
    0.44
    requests
    0.44
    ing
    0.44
    business
    0.44
    Activations Density 0.001%

    No Known Activations