© 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. 197827
    Prev
    Next
    INDEX
    Explanations

    admirable or successful

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

    legalized pirate

    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
     จำ
    0.61
     ถ้า
    0.54
     จํา
    0.53
     구매
    0.53
     따
    0.52
    ात
    0.52
     ด้วย
    0.52
     ทั้ง
    0.51
     ทำให้
    0.50
    คองโก
    0.50
    POSITIVE LOGITS
    ي
    0.51
     NAN
    0.46
    i
    0.42
    NAN
    0.42
    MUT
    0.42
    Someone
    0.42
     goof
    0.41
    PADDING
    0.40
    يلا
    0.40
    Se
    0.39
    Activations Density 0.000%

    No Known Activations