© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61155
    Prev
    Next
    INDEX
    Explanations

    ending words like нормально, важно, понятно

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    းက
    -2.66
    禔
    -2.33
    </h3>
    -2.25
            
    -2.25
    ᡵ
    -2.16
     услуг
    -2.09
     hinder
    -2.09
    訫
    -2.06
    🦣
    -2.03
    glazed
    -2.02
    POSITIVE LOGITS
    '
    3.02
    [
    2.34
    $
    2.33
    what
    2.19
    蕯
    2.11
    (
    2.03
     bądź
    2.03
    ta
    2.00
    梣
    2.00
    ,,,,
    1.99
    Activations Density 0.005%

    No Known Activations