© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 113
    Prev
    Next
    INDEX
    Explanations

    per followed by time unit

    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
     and
    1.30
    ,
    1.28
     mentality
    1.26
     severely
    1.24
     is
    1.23
     to
    1.22
     да
    1.21
     of
    1.21
     provide
    1.20
     disadvantaged
    1.19
    POSITIVE LOGITS
     prípade
    1.81
     případě
    1.80
    漃
    1.78
     sareng
    1.78
     ricerche
    1.78
     przedsiębior
    1.75
     związku
    1.75
     filóso
    1.74
    űt
    1.72
     trakcie
    1.69
    Activations Density 0.016%

    No Known Activations