© 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. 220269
    Prev
    Next
    INDEX
    Explanations

    items and descriptions

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

    Academics, extensions, differently, kept alone

    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
    adium
    0.50
    하며
    0.50
     SIINFEKL
    0.49
    anah
    0.48
    시키
    0.46
     黑
    0.46
    portál
    0.46
    焊
    0.46
     đấy
    0.46
    存在的
    0.45
    POSITIVE LOGITS
    carros
    0.47
    म्
    0.46
     boats
    0.42
     yachts
    0.41
     mixes
    0.40
     horrors
    0.40
     Yachts
    0.39
     celebrities
    0.39
     Conditions
    0.39
     discounts
    0.39
    Activations Density 0.000%

    No Known Activations