© 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. 57057
    Prev
    Next
    INDEX
    Explanations

    dangers to, detailed box, exclusive plain, dedicated scan

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

    concerns and explanations

    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
     vertreten
    0.52
    )}
    0.50
    }):
    0.48
     leistungs
    0.48
     سائ
    0.48
    knings
    0.47
    ស
    0.47
    ដែលមាន
    0.47
     Umgebung
    0.46
     коллеги
    0.46
    POSITIVE LOGITS
    矛
    0.47
    уго
    0.45
    յան
    0.44
     sides
    0.43
     lengthwise
    0.43
    끔
    0.43
    scope
    0.42
    бар
    0.42
    ել
    0.42
    utacji
    0.42
    Activations Density 0.000%

    No Known Activations