© 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. 16-GEMMASCOPE-2-RES-262K
    7. 41385
    Prev
    Next
    INDEX
    Explanations

    cumulative effect

    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_16_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
    oc
    1.15
    。
    1.14
    ’
    1.02
     I
    1.02
    اه
    1.00
    ।
    0.99
    ක්
    0.98
     Бүгенге
    0.98
    ες
    0.92
    ates
    0.90
    POSITIVE LOGITS
    ล
    1.16
     of
    1.16
     cumul
    1.09
     Cum
    1.01
     cumulative
    0.98
     cum
    0.97
     Accum
    0.95
     accum
    0.94
     on
    0.93
     accumulated
    0.92
    Activations Density 0.011%

    No Known Activations