© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9007
    Prev
    Next
    INDEX
    Explanations

    4, care, control, point

    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
     reen
    1.29
     gaps
    1.22
     생긴
    1.18
    檎
    1.06
    गत
    1.03
    та
    1.02
     torn
    1.02
    ہوری
    1.01
    قان
    1.01
    ко
    0.98
    POSITIVE LOGITS
    arsenic
    1.36
    히
    1.31
     forego
    1.31
    ignty
    1.31
     préférences
    1.30
    austral
    1.30
    er
    1.30
     forgo
    1.29
     kaks
    1.28
    ergy
    1.27
    Activations Density 0.000%

    No Known Activations