© 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. 158144
    Prev
    Next
    INDEX
    Explanations

    Spanish auditing experience

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

    cultural capital, higher than, commas

    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
    ológicos
    0.50
     G
    0.48
     ਆ
    0.46
     சிறிய
    0.45
     кандида
    0.45
     β
    0.45
     άλλα
    0.44
     repay
    0.43
     ሌሎች
    0.43
    目标
    0.43
    POSITIVE LOGITS
    甸
    0.53
    ഴിഞ്ഞ
    0.50
     ditentukan
    0.48
    льное
    0.46
    िष्ट
    0.45
    പം
    0.45
     moverse
    0.45
     dhatu
    0.44
    یل
    0.44
    ките
    0.44
    Activations Density 0.000%

    No Known Activations