© 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. 47528
    Prev
    Next
    INDEX
    Explanations

    time

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

    avoiding explicit sexual or graphic 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
     parks
    0.47
    8
    0.46
     colleges
    0.45
     shelters
    0.42
    imet
    0.41
     avenues
    0.41
     ellen
    0.41
    parks
    0.41
    icare
    0.41
    ۸
    0.40
    POSITIVE LOGITS
     消費
    0.50
     नाराज
    0.48
     Publikum
    0.48
    事前
    0.47
     দর্শক
    0.46
     দর্শকের
    0.46
    dummy
    0.46
     પ્રે
    0.45
     事
    0.45
     réussite
    0.45
    Activations Density 0.000%

    No Known Activations