© 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-262K
    7. 11791
    Prev
    Next
    INDEX
    Explanations

    latex commands: textbf, boxed

    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_262k_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
    weds
    3.02
    gehen
    2.84
    cı
    2.73
    
    2.66
    ıdır
    2.60
    े
    2.42
    agę
    2.39
    ことになる
    2.36
     hil
    2.33
    তা
    2.32
    POSITIVE LOGITS
    an
    2.48
    manner
    2.32
    hbox
    2.31
    𒁺
    2.18
    т
    2.04
    गुरु
    2.03
    ্ল্ড
    2.03
    ktu
    2.02
    ಾ
    2.02
    죄
    2.01
    Activations Density 0.002%

    No Known Activations