© 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. 115631
    Prev
    Next
    INDEX
    Explanations

    commas or full stops

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

    after `from`

    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
    覀
    0.45
     credence
    0.44
     مشخص
    0.42
    PushMatrix
    0.41
     biosphere
    0.41
    ذه
    0.40
     Precambrian
    0.40
    िक
    0.40
    Claude
    0.39
    ounid
    0.39
    POSITIVE LOGITS
    ।”
    0.57
    ।
    0.56
    ে
    0.52
    。”
    0.50
    ।’
    0.48
    ।'
    0.47
    äser
    0.47
    ။
    0.47
    ?”
    0.46
    ।"
    0.46
    Activations Density 0.000%

    No Known Activations