© 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. 3298
    Prev
    Next
    INDEX
    Explanations

    code and markup structures

    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
    GTUIKit
    2.10
     Ecusson
    2.06
     HTMLSc
    2.05
    䳕
    2.05
     inactivació
    2.04
     fdPar
    2.04
     antennis
    2.02
     中国证券投资基金业协会
    2.01
    ConstPtr
    2.01
     vyber
    2.00
    POSITIVE LOGITS
     country
    1.55
    p
    1.52
    ight
    1.52
     plant
    1.35
     and
    1.30
     Y
    1.28
    ,
    1.27
     ceiling
    1.27
    .
    1.26
     p
    1.25
    Activations Density 0.005%

    No Known Activations