© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 222302
    Prev
    Next
    INDEX
    Explanations

    superficial charm and manipulation

    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_40_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
    ূহ
    0.57
    Secrets
    0.43
    izdat
    0.42
     resolução
    0.42
     résoudre
    0.39
     puzz
    0.38
    嬸
    0.38
     اجيب
    0.38
    辂
    0.38
     ETH
    0.38
    POSITIVE LOGITS
     shallow
    0.55
     predatory
    0.51
     charm
    0.50
     Charming
    0.49
     Shallow
    0.48
    魅
    0.47
     Mach
    0.46
    魅力
    0.46
     charming
    0.45
     admiration
    0.45
    Activations Density 0.020%

    No Known Activations