© 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. 36805
    Prev
    Next
    INDEX
    Explanations

    uncertainty and doubt

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

    uncertainty and ambiguity

    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
    ദന
    0.46
     righteousness
    0.45
     brev
    0.45
    辏
    0.43
    夙
    0.43
    льт
    0.42
    狧
    0.41
     relev
    0.39
    ିକ
    0.39
    殊
    0.39
    POSITIVE LOGITS
     uncertainty
    1.56
     Uncertainty
    1.45
     uncertain
    1.41
    uncertain
    1.41
     incertid
    1.39
     Uncertain
    1.30
     uncertainties
    1.29
     অনিশ্চ
    1.16
     ambiguity
    1.09
     indetermin
    1.09
    Activations Density 0.098%

    No Known Activations