© 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. 22-GEMMASCOPE-2-RES-65K
    7. 5850
    Prev
    Next
    INDEX
    Explanations

    value or quality

    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_65k_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
     aina
    0.81
    iane
    0.76
     manchmal
    0.73
    కాల
    0.73
    大好き
    0.73
    യായിരുന്നു
    0.72
    iaux
    0.71
    鐏
    0.71
     kanya
    0.70
     Finest
    0.69
    POSITIVE LOGITS
     meaningful
    2.69
     meaningfully
    2.53
     decent
    2.37
     reasonably
    2.34
     reasonable
    2.31
     decently
    2.30
     appreciable
    2.26
     significant
    2.23
     viable
    2.22
     worthwhile
    2.12
    Activations Density 0.600%

    No Known Activations