© 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. 526
    Prev
    Next
    INDEX
    Explanations

    system qualities and attributes

    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
     "./
    1.39
     "*
    1.37
     "../
    1.37
     *"
    1.34
     "
    1.34
    쨰
    1.31
    ઠી
    1.31
    ็ต
    1.31
    ಕೋ
    1.26
    ada
    1.24
    POSITIVE LOGITS
     ged
    1.68
     والح
    1.63
     واست
    1.62
    thebetter
    1.59
     وغ
    1.49
    sourced
    1.47
    gefühl
    1.47
    และความ
    1.46
     AND
    1.45
     والإ
    1.45
    Activations Density 9.352%

    No Known Activations