© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 891
    Prev
    Next
    INDEX
    Explanations

    causes for blame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    arkhand
    1.73
    ämme
    1.67
     receivable
    1.62
     stamps
    1.60
    ៊
    1.58
     되어
    1.58
    piratory
    1.58
     Pertama
    1.58
    adients
    1.57
    })^{-
    1.57
    POSITIVE LOGITS
     обстоя
    2.23
     disso
    2.21
    __*/
    2.18
     absoluta
    2.17
    щего
    2.17
     nécessité
    2.16
    িকল্প
    2.16
    দেহ
    2.09
     Erkennt
    2.08
     circunstancias
    2.07
    Activations Density 1.950%

    No Known Activations