© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101325
    Prev
    Next
    INDEX
    Explanations

    End of phases or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    тер
    0.49
    విత
    0.49
     интеллек
    0.47
    ት
    0.47
    това
    0.47
     интел
    0.46
    Squirrel
    0.46
    Д
    0.46
    Cic
    0.46
    வல்
    0.45
    POSITIVE LOGITS
     usable
    0.45
     ulang
    0.43
     unix
    0.43
     aprobación
    0.43
     hops
    0.42
    rc
    0.42
     Bezug
    0.41
    pyridine
    0.41
     hout
    0.40
    unehmen
    0.40
    Activations Density 0.002%

    No Known Activations