© 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. 20508
    Prev
    Next
    INDEX
    Explanations

    control the training process

    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
    ק
    0.43
    هر
    0.40
    neis
    0.40
    ivät
    0.39
    冗
    0.39
    毎日
    0.39
    ᄐ
    0.39
    マス
    0.38
     зай
    0.38
     scandals
    0.38
    POSITIVE LOGITS
    local
    0.52
    site
    0.47
     somebody
    0.47
    you
    0.46
    locale
    0.46
     spirit
    0.46
     lokale
    0.46
    എ
    0.46
     e
    0.45
    cl
    0.45
    Activations Density 0.003%

    No Known Activations