© 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. 58155
    Prev
    Next
    INDEX
    Explanations

    professional relationship

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

    Dough and building

    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
    ڍ
    0.48
     Goy
    0.43
    ]，
    0.43
     gug
    0.43
     কি
    0.42
     Marino
    0.42
     Montoya
    0.42
     estimator
    0.41
     kaç
    0.41
    MATRIX
    0.41
    POSITIVE LOGITS
     प्रतिबद्ध
    0.50
    environmental
    0.49
    appliqu
    0.49
    <unused44>
    0.48
    evoluzione
    0.48
    hort
    0.47
    brook
    0.47
    lett
    0.46
     प्रदूषण
    0.44
     периоди
    0.44
    Activations Density 0.000%

    No Known Activations