© 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. 17-GEMMASCOPE-2-RES-16K
    4. 33
    Prev
    Next
    INDEX
    Explanations

    list items after punctuation

    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_17_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
    apabb
    1.02
    <unused264>
    1.00
    <unused977>
    1.00
    <unused1910>
    0.99
    apadani
    0.97
    <unused2040>
    0.96
    <unused105>
    0.95
    centred
    0.94
    <unused425>
    0.93
    <unused693>
    0.92
    POSITIVE LOGITS
     Both
    0.93
     Somit
    0.91
     Since
    0.85
     Because
    0.82
    これにより
    0.81
    もし
    0.81
     Additionally
    0.79
     بنابراین
    0.78
    そのため
    0.78
     Therefore
    0.78
    Activations Density 5.720%

    No Known Activations