© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9306
    Prev
    Next
    INDEX
    Explanations

    adult social and related contexts

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

    adult related contexts

    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_40_width_16k_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
     prog
    0.41
    Personnel
    0.41
    msbuild
    0.40
     Prog
    0.39
    Affected
    0.39
    九
    0.39
    Attribute
    0.39
    厭
    0.39
    elij
    0.38
     embargo
    0.38
    POSITIVE LOGITS
     Adult
    1.04
    adult
    1.01
    Adult
    0.99
     adult
    0.97
     Adults
    0.94
     adulto
    0.92
     adulta
    0.91
     adults
    0.91
    成人
    0.90
     dewasa
    0.88
    Activations Density 0.032%

    No Known Activations