© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14102
    Prev
    Next
    INDEX
    Explanations

    following punctuation or specific words

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

    for seminars or presentations

    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
    Super
    0.55
    zelf
    0.53
    ي
    0.53
    ల్
    0.50
     chied
    0.48
     Gewer
    0.46
    يي
    0.46
    Learning
    0.45
    渤
    0.45
    探讨
    0.45
    POSITIVE LOGITS
    식이
    0.50
     경우에는
    0.49
    점이
    0.48
    overleftarrow
    0.44
     그래
    0.43
     eigenvector
    0.43
     መቀ
    0.43
    avacanam
    0.43
    지지
    0.43
    心の
    0.43
    Activations Density 0.001%

    No Known Activations