© 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. 2320
    Prev
    Next
    INDEX
    Explanations

    introducing a story or topic

    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
     boundedness
    0.54
     館
    0.54
    ʾ
    0.52
     호텔
    0.50
     panggilan
    0.48
     Inference
    0.47
     bhai
    0.47
     deliberations
    0.47
     apoyar
    0.47
     Klan
    0.46
    POSITIVE LOGITS
     have
    0.47
    吗
    0.45
    c
    0.44
    款
    0.44
    v
    0.44
     человека
    0.43
    1
    0.42
    al
    0.42
    上
    0.42
    ad
    0.41
    Activations Density 0.054%

    No Known Activations