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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10757
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    가
    1.77
    leri
    1.67
    ε
    1.50
    ा
    1.34
    ೆಯ
    1.32
    li
    1.31
    ْم
    1.29
    lerin
    1.28
     harnesses
    1.25
    ize
    1.24
    POSITIVE LOGITS
    ନା
    1.56
     ′
    1.50
    ﻰ
    1.44
    }}\
    1.41
    }(\
    1.40
    '"
    1.39
    öglichkeiten
    1.38
    䀼
    1.38
    🏢
    1.36
    |}\
    1.35
    Activations Density 0.003%

    No Known Activations