© 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. 13877
    Prev
    Next
    INDEX
    Explanations

    according to

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

    Increased autistic traits

    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
    in
    0.53
    М
    0.51
     bat
    0.50
     zašt
    0.49
    Export
    0.47
    К
    0.47
    ミ
    0.47
    크
    0.47
    파
    0.47
    R
    0.46
    POSITIVE LOGITS
     Celebrating
    0.50
     positivos
    0.48
     అమ్మ
    0.48
     Instagram
    0.47
     Histogram
    0.47
     Banerjee
    0.47
     நிறுவனம்
    0.47
     instagram
    0.46
     Liabilities
    0.45
    ográficos
    0.45
    Activations Density 0.000%

    No Known Activations