© 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. 96852
    Prev
    Next
    INDEX
    Explanations

    Libya, Rutherford, contracts, acre

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

    problem statement or theorem

    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
    Disconnect
    0.49
     빨
    0.46
    })]
    0.46
     თან
    0.45
     incisions
    0.45
     yü
    0.44
    ęcz
    0.44
    的气
    0.43
     തൂ
    0.43
     برس
    0.42
    POSITIVE LOGITS
    никова
    0.50
    тился
    0.45
    ума
    0.45
    тились
    0.45
    𝘭
    0.45
    лев
    0.44
    новых
    0.43
     knack
    0.42
    лок
    0.42
     млад
    0.42
    Activations Density 0.000%

    No Known Activations