© 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. 161527
    Prev
    Next
    INDEX
    Explanations

    punctuation and orders

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

    sorry to hear

    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
     평가
    0.55
    룩
    0.53
    ۶
    0.49
    ۸
    0.48
     قاعدة
    0.47
     valutazione
    0.46
     ajout
    0.46
     kaynak
    0.46
     evaluate
    0.46
     evaluación
    0.46
    POSITIVE LOGITS
    不敢
    0.45
    s
    0.45
    酛
    0.43
    appar
    0.43
    究竟
    0.43
    ሒ
    0.42
    ichung
    0.41
    到底
    0.41
    類型
    0.41
    ren
    0.40
    Activations Density 0.000%

    No Known Activations