© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2517
    Prev
    Next
    INDEX
    Explanations

    evaluating factual statements

    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_31_width_16k_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
    7
    0.61
    6
    0.59
    4
    0.56
    5
    0.54
    9
    0.52
    8
    0.52
    3
    0.49
    ４
    0.47
    শ
    0.46
    1
    0.45
    POSITIVE LOGITS
     svoj
    0.45
     unorthodox
    0.45
    唧
    0.43
     misfort
    0.42
     postoje
    0.42
     ghar
    0.42
     socios
    0.42
     suatu
    0.41
     disequ
    0.41
     protagonist
    0.41
    Activations Density 0.888%

    No Known Activations