© 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. 225557
    Prev
    Next
    INDEX
    Explanations

    lists of articles and clauses

    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
     része
    0.49
    ധ്യ
    0.46
    }})$
    0.46
    例
    0.44
     getActivity
    0.43
    剷
    0.43
    ίσ
    0.43
    ധാന
    0.43
     amerik
    0.43
    如
    0.43
    POSITIVE LOGITS
    ">⁡</
    0.52
    ucin
    0.50
    watering
    0.48
    filtering
    0.48
     نخ
    0.47
    angor
    0.47
     واست
    0.47
     بال
    0.47
     गैर
    0.46
     ناک
    0.46
    Activations Density 0.000%

    No Known Activations