© 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. 74184
    Prev
    Next
    INDEX
    Explanations

    newspaper subscription

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

    applying after considering

    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
    serious
    0.44
     aggravating
    0.43
     saving
    0.43
     perfection
    0.42
     adventurers
    0.42
     irritating
    0.42
    -'].
    0.41
    logged
    0.41
     adventurous
    0.41
    ullie
    0.41
    POSITIVE LOGITS
     множе
    0.55
     múltiples
    0.54
    ミック
    0.52
     ديال
    0.52
    Cob
    0.51
     גי
    0.51
     छठ
    0.50
    𒁍
    0.50
     حصل
    0.50
     incluem
    0.49
    Activations Density 0.001%

    No Known Activations