© 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. 33349
    Prev
    Next
    INDEX
    Explanations

    Scalability, Epic vs. Story

    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
    must
    0.57
    would
    0.57
    invoice
    0.46
    wy
    0.46
    three
    0.46
    i
    0.46
    microphone
    0.46
    with
    0.46
    products
    0.46
    pip
    0.45
    POSITIVE LOGITS
    喤
    0.48
    澍
    0.47
     metaphor
    0.46
    ся
    0.45
    ంతి
    0.45
    ప్ప
    0.45
    本当
    0.45
    ైన
    0.45
    暗示
    0.45
     భారీ
    0.44
    Activations Density 0.003%

    No Known Activations