© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3135
    Prev
    Next
    INDEX
    Explanations

    handling empty

    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
     figur
    0.64
    ன்னா
    0.60
    ἦ
    0.59
     आंक
    0.57
    íso
    0.56
     Propulsion
    0.55
    éo
    0.55
    iton
    0.55
    sop
    0.54
     sop
    0.53
    POSITIVE LOGITS
     に
    0.70
     י
    0.68
     [{
    0.66
     overcrowded
    0.65
     soll
    0.65
     shal
    0.65
    detail
    0.64
     Trem
    0.63
    ⇆
    0.62
    岷
    0.62
    Activations Density 0.136%

    No Known Activations