© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2281
    Prev
    Next
    INDEX
    Explanations

    canada, maple, north america, CAD

    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
    ้
    3.39
     quotid
    2.96
    er
    2.84
    о
    2.79
    ان
    2.72
    ैंड
    2.70
    dang
    2.63
    ная
    2.61
    ون
    2.61
    ो
    2.60
    POSITIVE LOGITS
    ется
    2.96
    ⌞
    2.92
     bacon
    2.58
    ʟ
    2.56
    те
    2.53
    ᴛ
    2.47
    τες
    2.43
    ➘
    2.40
    িং
    2.39
    ✞
    2.38
    Activations Density 0.140%

    No Known Activations