© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12041
    Prev
    Next
    INDEX
    Explanations

    night observation or discovery

    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
    ed
    1.57
    ken
    1.54
    ht
    1.53
    omas
    1.50
    bul
    1.50
    나
    1.48
     problem
    1.44
     ed
    1.43
    ad
    1.42
     quite
    1.40
    POSITIVE LOGITS
    "+"|".
    2.48
    ɻ
    2.43
    ੩
    2.42
     spacerItem
    2.42
    <unused794>
    2.40
    <unused1365>
    2.38
     BLUENRG
    2.35
    <unused1928>
    2.35
    <unused1754>
    2.35
    <unused1203>
    2.32
    Activations Density 0.069%

    No Known Activations