© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8376
    Prev
    Next
    INDEX
    Explanations

    self-introduction as Gemma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     अध्यापक
    0.86
    ⿹
    0.80
     আইনজীবী
    0.80
     இலக்கிய
    0.77
    เ
    0.76
    ଐ
    0.76
    ቂ
    0.73
     промышлен
    0.73
     систему
    0.72
    ሼ
    0.72
    POSITIVE LOGITS
     filesize
    0.59
     numerically
    0.58
     seemingly
    0.56
     insofar
    0.56
     proof
    0.55
     lower
    0.54
     teething
    0.54
     timing
    0.54
     qualitatively
    0.53
     phasing
    0.51
    Activations Density 0.030%

    No Known Activations