© 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. 116423
    Prev
    Next
    INDEX
    Explanations

    smart team qualified senior

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

    overtly sexual content

    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
    vature
    0.52
    Lowest
    0.49
    osal
    0.48
    osum
    0.48
    䪱
    0.47
     Overseas
    0.47
    sass
    0.47
    ariance
    0.47
    Overse
    0.46
    Rationale
    0.46
    POSITIVE LOGITS
    ध्व
    0.45
     city
    0.44
    ))^
    0.44
    банк
    0.42
     wholly
    0.42
     adverts
    0.42
    ります
    0.41
     marque
    0.41
    ები
    0.40
    ummies
    0.40
    Activations Density 0.000%

    No Known Activations