© 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. 13441
    Prev
    Next
    INDEX
    Explanations

    asking about speaking languages

    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
     पदार्थों
    0.68
    체
    0.68
    тера
    0.64
     lexic
    0.63
    uffix
    0.63
    HELP
    0.63
    Transpose
    0.63
    DONE
    0.62
     transpose
    0.61
    못
    0.61
    POSITIVE LOGITS
     fluent
    0.99
     kein
    0.92
     business
    0.92
    business
    0.89
     impeccable
    0.89
     سرکاری
    0.87
    official
    0.86
     Business
    0.84
     bisnis
    0.83
     flawless
    0.83
    Activations Density 0.036%

    No Known Activations