© 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. 74369
    Prev
    Next
    INDEX
    Explanations

    promo code, coupon

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

    travel down, example is

    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
    리가
    0.51
    দানে
    0.47
    기가
    0.46
    λο
    0.45
    드가
    0.43
    스가
    0.43
    ﾈ
    0.42
    قبال
    0.42
    이가
    0.41
     posséd
    0.41
    POSITIVE LOGITS
    銚
    0.50
    robi
    0.48
     नतीजा
    0.48
    i
    0.46
     čini
    0.46
    یرو
    0.45
    ways
    0.45
    inar
    0.45
     हिस्ट्री
    0.45
     informativo
    0.44
    Activations Density 0.000%

    No Known Activations