© 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. 194058
    Prev
    Next
    INDEX
    Explanations

    team andam learning

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

    AI content detection

    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
     kaart
    0.51
    شان
    0.50
     getSize
    0.48
     🙏
    0.47
     softness
    0.47
    NOM
    0.47
     getDate
    0.46
    즌
    0.46
     slipping
    0.46
     कलम
    0.46
    POSITIVE LOGITS
    i
    0.50
     Peripheral
    0.47
    ли
    0.44
     Mechanisms
    0.43
    Peripheral
    0.43
    ILS
    0.42
     universitaria
    0.42
    ai
    0.40
     setw
    0.40
     یونیورسٹی
    0.40
    Activations Density 0.001%

    No Known Activations