© 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. 189946
    Prev
    Next
    INDEX
    Explanations

    awards or deductions

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

    sexual arousal and bodily sensations

    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
    述
    0.49
    ール
    0.47
    င်း
    0.46
    ッチ
    0.46
    рі
    0.45
    ました
    0.44
    ーパー
    0.44
    爾
    0.44
    رات
    0.43
    തിക
    0.43
    POSITIVE LOGITS
    AG
    0.54
     যু
    0.51
     adsorb
    0.51
     youths
    0.50
     זה
    0.49
    AGING
    0.48
     overcrow
    0.48
     уте
    0.48
     inadequ
    0.47
     קי
    0.47
    Activations Density 0.002%

    No Known Activations