© 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. 94
    Prev
    Next
    INDEX
    Explanations

    instructions and advice

    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
    (/(
    2.25
     strCmd
    2.11
     contratto
    2.00
    Earnings
    1.97
    আমর
    1.96
     lighten
    1.96
    Compressed
    1.95
     ofrec
    1.95
    伨
    1.94
    ioxide
    1.93
    POSITIVE LOGITS
    rd
    1.33
    rig
    1.31
     percolation
    1.27
    rasi
    1.27
     Dose
    1.26
    ubar
    1.24
     metropolis
    1.22
    zag
    1.22
    ომ
    1.22
     Or
    1.22
    Activations Density 0.000%

    No Known Activations