© 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-262K
    7. 3831
    Prev
    Next
    INDEX
    Explanations

    sex, control, losing

    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_262k_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
    畂
    0.53
     особливо
    0.52
     உய
    0.52
    ✷
    0.48
    certificado
    0.47
     ವರ್ಷ
    0.47
    tım
    0.47
    決勝
    0.46
     जैव
    0.46
    lcii
    0.46
    POSITIVE LOGITS
    3
    0.56
    نا
    0.54
    ва
    0.50
    4
    0.49
    ние
    0.45
    нами
    0.45
    но
    0.44
    ек
    0.44
    بة
    0.43
    omen
    0.43
    Activations Density 0.001%

    No Known Activations