© 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. 57160
    Prev
    Next
    INDEX
    Explanations

    currency amounts and specific locations

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

    words including specific entities

    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
    וני
    0.55
    秽
    0.48
    gares
    0.47
    òria
    0.45
    atmosphère
    0.43
    óloga
    0.42
    Ნ
    0.41
    وامی
    0.41
    OLOGICAL
    0.41
    acart
    0.41
    POSITIVE LOGITS
     (<
    0.46
     (~
    0.44
     इनमें
    0.44
    ইন
    0.40
     including
    0.39
     unterwegs
    0.38
     včetně
    0.38
     लौट
    0.37
    inson
    0.37
    (<
    0.37
    Activations Density 0.000%

    No Known Activations