© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13214
    Prev
    Next
    INDEX
    Explanations

    precise dimension, opportunity before, announcements have

    np_acts-logits-general · gemini-2.5-flash-lite

    often appreciate, selling, experiencing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    渚
    0.47
    hr
    0.45
    gambar
    0.42
    a
    0.42
     prer
    0.41
    :
    0.41
     I
    0.41
    ウィ
    0.40
     किन्तु
    0.40
    :>
    0.40
    POSITIVE LOGITS
    <end_of_turn>
    0.50
    পদের
    0.49
    ете
    0.48
    єте
    0.48
    蜚
    0.47
    гада
    0.46
    ูล
    0.46
    <unused1844>
    0.46
    èves
    0.46
    েবের
    0.46
    Activations Density 0.005%

    No Known Activations