© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 82226
    Prev
    Next
    INDEX
    Explanations

    we express confidence or belief

    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_53_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
     am
    0.55
     observed
    0.50
     noticed
    0.49
     observe
    0.45
     cannot
    0.45
     signify
    0.44
     jsem
    0.42
    "%>
    0.41
     decide
    0.41
     witnessed
    0.41
    POSITIVE LOGITS
     confidence
    0.52
     confident
    0.49
    confidence
    0.48
    confident
    0.47
     Confidence
    0.46
    ALERT
    0.46
    Confident
    0.44
    薦
    0.44
    Invite
    0.43
     уверен
    0.43
    Activations Density 0.002%

    No Known Activations