© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221611
    Prev
    Next
    INDEX
    Explanations

    linkedin info

    np_acts-logits-general · gemini-2.5-flash-lite

    FTC, community, expansions, Windows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     slimy
    0.46
     calci
    0.45
    过多
    0.44
     trailer
    0.42
    쑹
    0.42
     slush
    0.41
    播
    0.41
     bully
    0.41
    筛
    0.41
     fatten
    0.41
    POSITIVE LOGITS
     दक्षिण
    0.52
     विषय
    0.51
     dvoj
    0.51
     між
    0.50
    之間的
    0.50
     فهر
    0.49
     चिंता
    0.49
     জাগ্র
    0.49
     ਦ
    0.48
     ذکر
    0.48
    Activations Density 0.000%

    No Known Activations