© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14415
    Prev
    Next
    INDEX
    Explanations

    computational and abstract concepts

    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_13_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
     motionless
    1.25
    dzić
    1.25
    部的
    1.24
     permissible
    1.22
     nonspecific
    1.20
    
    1.18
     Seventh
    1.17
    CYCLE
    1.15
    ̕
    1.15
     numberWithFloat
    1.14
    POSITIVE LOGITS
    priv
    1.08
     Tele
    1.03
    hor
    1.02
    Tele
    1.01
     pela
    1.00
     pelos
    0.99
    vid
    0.98
     pelas
    0.97
     paru
    0.97
    yng
    0.95
    Activations Density 0.000%

    No Known Activations