© 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. 2087
    Prev
    Next
    INDEX
    Explanations

    temporal sequences

    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
     불구하고
    2.45
     dawn
    2.40
     kwargs
    2.33
    しょう
    2.24
     rewritten
    2.22
     importantly
    2.15
    在
    2.10
    గానే
    2.07
    𝒕
    1.99
    heen
    1.97
    POSITIVE LOGITS
    ು
    3.29
    н
    3.19
    т
    3.02
    d
    2.97
    ০
    2.92
    ли
    2.81
    ר
    2.77
    an
    2.66
    ه
    2.65
    ت
    2.61
    Activations Density 0.028%

    No Known Activations