© 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-262K
    7. 218927
    Prev
    Next
    INDEX
    Explanations

    makes silk

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

    blooms, ideologically divided, between

    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_262k_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
     চার্জ
    0.48
    ндарт
    0.43
     ถ้า
    0.43
    ชค
    0.43
    ラスト
    0.42
    勖
    0.42
    λώ
    0.41
    คโนโลยี
    0.41
    틱
    0.40
    휀
    0.39
    POSITIVE LOGITS
    make
    0.47
     Silk
    0.46
     make
    0.44
     devolved
    0.43
     Makes
    0.43
    making
    0.41
     silk
    0.39
     making
    0.38
     unveiling
    0.38
    makes
    0.37
    Activations Density 0.000%

    No Known Activations