© 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. 163222
    Prev
    Next
    INDEX
    Explanations

    geography and business entities

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

    potential concerns and distress

    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
     prostit
    0.49
    阉
    0.47
    邪魔
    0.47
    ibet
    0.47
    ewomen
    0.46
    തിനാൽ
    0.46
     souten
    0.45
    它們
    0.45
    rbrakk
    0.45
    ﾝ
    0.45
    POSITIVE LOGITS
     data
    0.51
     CSO
    0.48
     information
    0.47
     SAP
    0.45
     Information
    0.45
     LEON
    0.44
     Phone
    0.43
     PAP
    0.43
     phone
    0.43
     Original
    0.43
    Activations Density 0.002%

    No Known Activations