© 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. 11399
    Prev
    Next
    INDEX
    Explanations

    cruises and kayaking

    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
    م
    4.34
    ই
    4.25
    ten
    4.07
    ti
    3.67
    ्स
    3.57
    nya
    3.44
    tains
    3.31
    습니다
    3.22
    tained
    3.13
    رہ
    3.08
    POSITIVE LOGITS
    ు
    3.66
    hounds
    3.10
    ния
    3.05
    л
    2.98
    u
    2.81
     desperately
    2.66
    hound
    2.59
    놈
    2.55
     hyperplane
    2.49
    та
    2.47
    Activations Density 0.060%

    No Known Activations