© 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. 31-GEMMASCOPE-2-RES-262K
    7. 203022
    Prev
    Next
    INDEX
    Explanations

    unsigned integer

    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
     France
    0.45
     genius
    0.44
     soporte
    0.43
     stampa
    0.43
     IM
    0.43
     LEG
    0.43
     escalated
    0.42
    鯵
    0.42
     prove
    0.42
     کوئی
    0.42
    POSITIVE LOGITS
    ointing
    0.53
    ituation
    0.51
    allel
    0.50
    iben
    0.50
    ibt
    0.48
    elő
    0.48
    ically
    0.47
    ándose
    0.47
    asking
    0.47
    oint
    0.46
    Activations Density 0.001%

    No Known Activations