© 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. 14297
    Prev
    Next
    INDEX
    Explanations

    AI model examples

    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
    <unused2020>
    1.97
    েন্দ্রলাল
    1.91
    显著
    1.80
    <unused1950>
    1.76
    <unused1666>
    1.75
    <unused900>
    1.74
    liel
    1.73
    .|__
    1.73
    <unused1702>
    1.69
    <unused752>
    1.69
    POSITIVE LOGITS
     sedang
    1.30
     awaiting
    1.19
     Pipeline
    1.17
     T
    1.16
    s
    1.16
     rumoured
    1.16
     Ch
    1.15
     Organic
    1.13
     Market
    1.12
     percol
    1.12
    Activations Density 0.328%

    No Known Activations