© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 42667
    Prev
    Next
    INDEX
    Explanations

    Hope Charity, long way, bit of

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

    dry ingredients, first person, classic riddle

    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
    ]'
    0.49
    ﺟ
    0.45
     superiori
    0.44
    *'
    0.41
     convicted
    0.41
     ++
    0.41
    Sorted
    0.41
     ’
    0.40
     justices
    0.40
     بک
    0.39
    POSITIVE LOGITS
    尷
    0.50
    尴尬
    0.49
    ades
    0.47
    ιά
    0.46
    ាតុ
    0.45
    吆
    0.44
    še
    0.43
     పంట
    0.43
     africa
    0.43
    asmine
    0.43
    Activations Density 0.000%

    No Known Activations