© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2110
    Prev
    Next
    INDEX
    Explanations

    self-reflection and self-discovery

    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
    чика
    0.56
    ertos
    0.55
    OMO
    0.54
    ática
    0.53
     clings
    0.53
     সেনা
    0.52
    <0x8B>
    0.52
    ielo
    0.52
    classlist
    0.52
    meleri
    0.51
    POSITIVE LOGITS
    announced
    0.77
    簾
    0.63
    はじめ
    0.63
     going
    0.61
     épu
    0.61
    효
    0.61
     assurance
    0.61
     center
    0.61
    South
    0.59
    篦
    0.58
    Activations Density 0.442%

    No Known Activations