© 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. 21392
    Prev
    Next
    INDEX
    Explanations

    sexual assault hotline

    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
     temperatures
    0.50
     boundedness
    0.50
     corticosteroids
    0.49
     leaked
    0.48
     apoptosis
    0.48
     hydrochloric
    0.48
     introns
    0.47
    θ
    0.47
     lepton
    0.47
     palco
    0.47
    POSITIVE LOGITS
     الصورة
    0.47
     Samantha
    0.46
     Marke
    0.46
     સહિત
    0.46
     படம்
    0.45
     illetve
    0.45
     وكذلك
    0.43
    credential
    0.43
     તથા
    0.43
    த்திலும்
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.