© 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. 131567
    Prev
    Next
    INDEX
    Explanations

    months ago

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

    means diverse

    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
    ก
    0.50
    Е
    0.48
     अफसर
    0.46
    મ
    0.46
    被迫
    0.45
    লে
    0.44
    Ε
    0.44
    자
    0.44
    すべて
    0.43
    きれい
    0.43
    POSITIVE LOGITS
     separa
    0.45
     Sep
    0.43
    rivate
    0.43
     Whether
    0.42
     But
    0.42
    anker
    0.41
     According
    0.41
     Wasn
    0.41
     behest
    0.41
    žení
    0.40
    Activations Density 0.000%

    No Known Activations