© 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. 83362
    Prev
    Next
    INDEX
    Explanations

    technical terms and function names

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

    protocols for IoT devices

    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
     quarrel
    0.50
     riferimento
    0.46
    癖
    0.45
    orney
    0.45
     jurisprudence
    0.44
    ෲ
    0.43
     prawd
    0.42
    ಲೆ
    0.42
    ری
    0.42
    ੍ਰ
    0.41
    POSITIVE LOGITS
     Routed
    0.48
     replacements
    0.44
     xScale
    0.42
     замі
    0.42
     installed
    0.41
     замени
    0.41
     compressors
    0.40
     useRouter
    0.40
    ...*/
    0.39
    GING
    0.39
    Activations Density 0.000%

    No Known Activations