© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2994
    Prev
    Next
    INDEX
    Explanations

    placeholders and specific names

    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_29_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
     örnek
    0.84
    मंद
    0.79
    example
    0.79
     invention
    0.78
     informativo
    0.77
    ínez
    0.77
     example
    0.77
    .~\
    0.76
    ＊＊
    0.76
     dilemma
    0.75
    POSITIVE LOGITS
    ιδ
    0.71
     පු
    0.68
     שנה
    0.67
    вища
    0.64
     nomin
    0.63
    ថ្
    0.62
     formada
    0.62
     judges
    0.60
    种
    0.58
     nominations
    0.58
    Activations Density 0.063%

    No Known Activations