© 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. 22-GEMMASCOPE-RES-131K
    7. 12905
    Prev
    Next
    INDEX
    Explanations

    Numbers and punctuation

    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_22/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
    Người
    -1.20
    ungkin
    -1.16
    пс
    -1.14
    ⌂
    -1.06
     LCCN
    -1.04
     my
    -1.04
    indahan
    -1.04
    ᾷ
    -1.02
    Fordítás
    -1.02
    橈
    -1.01
    POSITIVE LOGITS
    場所で
    1.09
     hjælpe
    1.08
    溼
    1.07
    ins
    1.05
    ha
    1.02
    en
    1.00
     總
    1.00
    ess
    1.00
    _
    0.99
     مشکی
    0.98
    Activations Density 0.000%

    No Known Activations