© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10395
    Prev
    Next
    INDEX
    Explanations

    generated

    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
     fonctionner
    1.77
     intravenously
    1.57
    ейчас
    1.56
    ۤ
    1.49
     angst
    1.49
    ▸
    1.47
    ч
    1.45
    ⁃
    1.45
    и
    1.45
    ση
    1.42
    POSITIVE LOGITS
    et
    1.72
    tion
    1.44
    skill
    1.32
    esign
    1.31
    ead
    1.28
    sers
    1.24
    es
    1.24
    ｩ
    1.22
     Increasing
    1.21
     stenosis
    1.20
    Activations Density 0.000%

    No Known Activations