© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65
    Prev
    Next
    INDEX
    Explanations

    print statements and code output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ASHINGTON
    0.30
    ➛
    0.29
    şiktaş
    0.29
     pInBuffer
    0.28
     NSURL
    0.28
    🚃
    0.28
    ası
    0.27
    కొ
    0.27
     CHLOR
    0.27
    şi
    0.27
    POSITIVE LOGITS
    G
    0.39
    T
    0.35
    H
    0.34
    n
    0.33
    a
    0.31
    re
    0.31
    d
    0.31
    D
    0.30
    V
    0.30
    x
    0.30
    Activations Density 0.001%

    No Known Activations