© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 991
    Prev
    Next
    INDEX
    Explanations

    identifying places

    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_9_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
    ت
    1.88
    ted
    1.70
    ્સ
    1.66
    kannya
    1.64
    Ο
    1.61
    трим
    1.56
    tion
    1.55
    sine
    1.54
    nya
    1.53
    nouns
    1.52
    POSITIVE LOGITS
    員
    1.48
    ें
    1.46
    goed
    1.45
     trưng
    1.41
    icu
    1.40
    ጀመሪያ
    1.38
    ка
    1.37
     svare
    1.37
    ந்த
    1.36
     الماض
    1.36
    Activations Density 0.422%

    No Known Activations