© 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. 150269
    Prev
    Next
    INDEX
    Explanations

    claims and factual statements

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

    justification is insufficient

    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
    longer
    0.45
    ość
    0.44
    alem
    0.44
    برای
    0.44
    大きい
    0.43
    wayne
    0.43
    Ｉ
    0.42
    ESS
    0.42
    enn
    0.41
    ennen
    0.41
    POSITIVE LOGITS
     pretext
    0.48
     此
    0.48
     falsehood
    0.47
     只
    0.46
     proposition
    0.44
    InProgress
    0.43
     pretended
    0.43
     superstition
    0.42
     exposition
    0.42
     dish
    0.41
    Activations Density 0.002%

    No Known Activations