© 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. 22-GEMMASCOPE-2-RES-262K
    7. 3235
    Prev
    Next
    INDEX
    Explanations

    don't mention being an ai model

    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_22_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
     Ведь
    0.64
    whereas
    0.62
     Whereas
    0.61
     Ceux
    0.56
     ведь
    0.55
     Asimismo
    0.55
     ś
    0.54
    〔
    0.54
    nocześnie
    0.53
    ('${
    0.53
    POSITIVE LOGITS
    Maintenance
    0.49
    Describe
    0.48
    Define
    0.45
     idiom
    0.45
    שהו
    0.45
     nhìn
    0.45
    etry
    0.43
    Adapt
    0.43
    LL
    0.43
    Init
    0.43
    Activations Density 0.163%

    No Known Activations