© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 143
    Prev
    Next
    INDEX
    Explanations

    space, legality, science, process

    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
    هام
    1.44
    为
    1.36
     difficultés
    1.34
    蘭
    1.28
     difficulties
    1.27
     composição
    1.26
    為
    1.26
     mengucapkan
    1.24
    を
    1.23
     rè
    1.23
    POSITIVE LOGITS
     Закон
    1.80
    raped
    1.79
    ϩ
    1.78
    ylar
    1.78
    ଙ
    1.77
    ˟
    1.76
    uvo
    1.72
    ➔
    1.69
    ucket
    1.68
    γωγ
    1.68
    Activations Density 0.000%

    No Known Activations