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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4076
    Prev
    Next
    INDEX
    Explanations

    bad or poor quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     cukup
    0.82
     rarity
    0.72
    尕
    0.69
    Jlc
    0.68
     transcend
    0.68
     suficiente
    0.67
    batasan
    0.66
     বাহিরে
    0.66
    ":[
    0.66
    Multicolored
    0.65
    POSITIVE LOGITS
     bad
    1.96
     Bad
    1.89
    Bad
    1.84
    bad
    1.81
    Poor
    1.70
     BAD
    1.67
     Poor
    1.65
     poor
    1.62
     worse
    1.58
     terrible
    1.52
    Activations Density 0.338%

    No Known Activations