© 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. 32506
    Prev
    Next
    INDEX
    Explanations

    sexual content and related context

    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
     Hmm
    0.48
     flocked
    0.45
     gdy
    0.43
     rarity
    0.43
     अहिले
    0.43
     Wanneer
    0.42
     Beaut
    0.42
    玻
    0.41
     Oops
    0.40
     volto
    0.40
    POSITIVE LOGITS
     তত্ত্বাব
    0.47
    Sexual
    0.46
    autogui
    0.46
     dehuman
    0.43
    онів
    0.43
    kbeta
    0.43
    isiert
    0.42
     дальнейшем
    0.42
    isierten
    0.42
     estará
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.