© 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. 155356
    Prev
    Next
    INDEX
    Explanations

    words followed by structure words

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

    urgent, pressing, critical

    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
     বোমা
    0.46
    arq
    0.46
     minifyEnabled
    0.46
     legitt
    0.46
     glBindTexture
    0.44
    গ্
    0.42
    𝗕
    0.42
    ＰＥ
    0.42
    Paste
    0.42
    PEG
    0.41
    POSITIVE LOGITS
    teller
    0.49
    銥
    0.45
    </h3>
    0.44
     vân
    0.44
    نات
    0.43
    s
    0.43
     ആദ്യ
    0.43
     temptations
    0.43
    lieder
    0.42
     العربي
    0.40
    Activations Density 0.000%

    No Known Activations