© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3031
    Prev
    Next
    INDEX
    Explanations

    asking for more information

    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
    厝
    2.00
    św
    1.88
     مرح
    1.82
     estánd
    1.79
    Dashboard
    1.78
     ورځې
    1.78
    。“
    1.77
    ликт
    1.75
    haan
    1.75
    --“
    1.75
    POSITIVE LOGITS
     rifle
    3.81
     ammunition
    3.52
     rifles
    3.43
     ammo
    3.41
     firearms
    3.31
     handgun
    3.30
     firearm
    3.21
    rifle
    3.18
     pistol
    3.15
     weapons
    2.94
    Activations Density 0.159%

    No Known Activations