© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 220056
    Prev
    Next
    INDEX
    Explanations

    generated page; month; partners; CTC; CA

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

    options for different budgets

    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
    德
    0.50
    ុក
    0.47
    躬
    0.46
    areti
    0.45
    šel
    0.45
     rediscover
    0.44
     IANS
    0.44
     rediscovered
    0.44
    ാമ
    0.44
    ukin
    0.43
    POSITIVE LOGITS
    Generated
    0.53
    generated
    0.51
    ケイ
    0.47
    꼴
    0.46
    生成的
    0.45
     پیچ
    0.45
    Generate
    0.44
     càng
    0.44
     Winning
    0.43
    folge
    0.42
    Activations Density 0.001%

    No Known Activations