© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    language version

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

    Electricity, Antibody, 声音

    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
     quinoa
    0.45
     barter
    0.45
     sporad
    0.44
     mohabbat
    0.43
     अल्प
    0.41
    ジル
    0.41
    aeskeygenassist
    0.41
    玷
    0.40
     نهاية
    0.40
     longterm
    0.40
    POSITIVE LOGITS
     Electricity
    0.47
     Informatics
    0.46
    的声音
    0.44
    声音
    0.42
     Voice
    0.42
    及时
    0.42
    工程师
    0.42
     voice
    0.41
    Voice
    0.41
     کہ
    0.41
    Activations Density 0.000%

    No Known Activations