© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6045
    Prev
    Next
    INDEX
    Explanations

    consent and willingness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     틀
    0.46
    斬
    0.41
    diagnosis
    0.41
     দরকার
    0.40
     ಸಾಧ
    0.39
    ॉफ्ट
    0.38
     경영
    0.38
     질
    0.38
     prognosis
    0.37
    pit
    0.37
    POSITIVE LOGITS
     consent
    1.16
     voluntary
    1.08
     voluntarily
    1.06
    Consent
    1.05
     Consent
    1.02
     consents
    0.98
     willingly
    0.97
     consentimiento
    0.97
     Voluntary
    0.96
    consent
    0.92
    Activations Density 0.636%

    No Known Activations