© 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. 1160
    Prev
    Next
    INDEX
    Explanations

    tools and agents

    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
    𝒌
    2.93
    ming
    2.87
    simeq
    2.87
    માં
    2.87
    𝑠
    2.85
    いる
    2.85
    하여
    2.72
    spect
    2.72
    sulf
    2.69
    וש
    2.66
    POSITIVE LOGITS
    l
    4.09
    رر
    3.92
    ্সের
    3.45
    lebnis
    3.42
    ل
    3.42
    ্স
    3.29
    عند
    3.26
    er
    3.15
    い
    3.10
    gebnis
    3.08
    Activations Density 0.897%

    No Known Activations