© 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. 283
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    hand
    1.99
    o
    1.86
    port
    1.82
    haus
    1.69
    oe
    1.65
    יות
    1.63
    דים
    1.62
    ­
    1.62
    ponent
    1.59
     and
    1.59
    POSITIVE LOGITS
    দ্ম
    2.35
    <unused2222>
    2.30
    ्ठा
    2.27
    ल्पनिक
    2.22
    使得
    2.17
    inerary
    2.16
    চ্ছিল
    2.14
    stdlib
    2.14
    ޚ
    2.14
    elligence
    2.13
    Activations Density 4.736%

    No Known Activations