© 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. 17-GEMMASCOPE-2-RES-16K
    7. 6080
    Prev
    Next
    INDEX
    Explanations

    bool and fizzbuzz

    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
    ćeg
    1.53
    𝜃
    1.44
    𝐕
    1.30
    𝙉
    1.29
    𝙎
    1.28
    𝘿
    1.26
     μας
    1.24
    𝐃
    1.23
    𝐀
    1.23
    𝐑
    1.21
    POSITIVE LOGITS
    er
    1.48
     incomplete
    1.16
    erious
    1.06
    ت
    1.01
     abduction
    1.01
     precedence
    1.00
     stri
    0.98
     effectually
    0.96
     equivalent
    0.95
    eram
    0.94
    Activations Density 0.022%

    No Known Activations