© 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. 77046
    Prev
    Next
    INDEX
    Explanations

    By and nominated

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

    identify trends

    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
    ޏ
    0.50
    কেন
    0.49
    鰓
    0.49
     HTMLSc
    0.47
    toISOString
    0.47
    FeO
    0.46
    
    0.46
     oxy
    0.46
     tránh
    0.45
     သူမ
    0.45
    POSITIVE LOGITS
    hoch
    0.44
     harmonization
    0.42
    яд
    0.40
    嘉
    0.39
    ى
    0.38
    z
    0.38
    जान
    0.38
     Hoc
    0.38
     Lafayette
    0.37
    umont
    0.37
    Activations Density 0.002%

    No Known Activations