© 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. 49497
    Prev
    Next
    INDEX
    Explanations

    defining phrases with "IT:"

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

    block, streamline, menu, data, sin

    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
     устойчи
    0.45
     వచ్చి
    0.43
    身份
    0.43
     разработан
    0.42
     존재하는
    0.42
     역할을
    0.42
    ☭
    0.41
    独特的
    0.40
    ุก
    0.40
    的角色
    0.40
    POSITIVE LOGITS
    0.53
    times
    0.50
    tagged
    0.48
    Times
    0.47
    >×</
    0.47
     ঢেউ
    0.47
    গি
    0.45
     precau
    0.45
     letra
    0.45
     referral
    0.44
    Activations Density 0.000%

    No Known Activations