© 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-262K
    7. 6971
    Prev
    Next
    INDEX
    Explanations

    range, probability, current, target

    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_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
     đều
    0.45
    obnie
    0.42
     çeşit
    0.42
     sorun
    0.41
    难
    0.41
     problemen
    0.41
     সমস্যায়
    0.41
    这边
    0.41
    法轮
    0.40
    驷
    0.40
    POSITIVE LOGITS
     highest
    0.58
     current
    0.55
     estimated
    0.55
     your
    0.55
    current
    0.54
     amount
    0.54
    total
    0.54
     perceived
    0.53
     value
    0.50
     weighted
    0.50
    Activations Density 0.314%

    No Known Activations