© 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. 168320
    Prev
    Next
    INDEX
    Explanations

    boys, surprising, and dark descriptions

    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
     ст
    0.51
    Р
    0.51
     господар
    0.48
    ᠴ
    0.48
     стара
    0.46
     уг
    0.45
     журнали
    0.45
    слан
    0.44
     я
    0.44
     pretending
    0.44
    POSITIVE LOGITS
    u
    0.71
    i
    0.57
    o
    0.56
    ak
    0.51
    he
    0.50
    uwa
    0.48
    imi
    0.48
    chester
    0.47
     Top
    0.46
     Poem
    0.46
    Activations Density 0.000%

    No Known Activations