© 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. 70823
    Prev
    Next
    INDEX
    Explanations

    rather + adjective

    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
     such
    -1.70
    ?
    -1.55
    的那个
    -1.50
    ]
    -1.48
     добраться
    -1.47
    Such
    -1.45
    '
    -1.43
    —
    -1.41
    ・・・」
    -1.41
    相应
    -1.40
    POSITIVE LOGITS
     Houſe
    1.71
    לה
    1.63
     verborgen
    1.53
    她
    1.53
     gekle
    1.47
    怏
    1.46
     geheim
    1.45
    если
    1.44
    יש
    1.41
     donker
    1.41
    Activations Density 0.009%

    No Known Activations