© 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. 37525
    Prev
    Next
    INDEX
    Explanations

    concept, explain, core, because

    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
     도
    0.41
    nesia
    0.41
     고급
    0.41
    >{
    0.40
     これらの
    0.40
    េ
    0.40
    ipelago
    0.40
     потер
    0.40
     toolPath
    0.40
    nonlinear
    0.39
    POSITIVE LOGITS
    ي
    0.45
     facilitar
    0.44
     защото
    0.44
    ですし
    0.43
    غي
    0.42
    верса
    0.42
    ப்பிட
    0.42
     बताता
    0.42
    사인
    0.42
     deoarece
    0.42
    Activations Density 0.003%

    No Known Activations