© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11391
    Prev
    Next
    INDEX
    Explanations

    taxi or axis

    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_13_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
    say
    0.91
     проєкту
    0.88
    Say
    0.81
     saying
    0.79
     проє
    0.77
    猗
    0.73
     Büh
    0.72
     alumnus
    0.71
     الوزن
    0.70
    ی
    0.70
    POSITIVE LOGITS
     corral
    0.84
     modestly
    0.83
     hairpin
    0.79
     weakly
    0.79
    Repr
    0.77
    ochlorite
    0.76
    낀
    0.75
     सौ
    0.74
    untlet
    0.74
     سوق
    0.74
    Activations Density 0.006%

    No Known Activations