© 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. 22258
    Prev
    Next
    INDEX
    Explanations

    trust expressions and worthiness

    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
    自信
    0.57
     confidently
    0.47
     уверен
    0.46
     Confidence
    0.42
    信心
    0.42
    勎
    0.41
     confidence
    0.41
    pción
    0.41
    <0x0D>
    0.40
     confident
    0.40
    POSITIVE LOGITS
    WORTH
    0.59
    worthy
    0.55
    TRUST
    0.54
    Tr
    0.54
    イ
    0.54
    ल्ल
    0.52
    oblasts
    0.50
    ल
    0.49
    न्न
    0.48
    ン
    0.48
    Activations Density 0.009%

    No Known Activations