© 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. 12431
    Prev
    Next
    INDEX
    Explanations

    number of

    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
     aesthetic
    1.17
     elizabeth
    1.11
    aesthetic
    1.10
     STYLE
    1.03
    chette
    1.02
     gothic
    1.01
     aesthetics
    1.00
    ;
    0.99
     gore
    0.99
    ubuntu
    0.99
    POSITIVE LOGITS
     calcule
    1.64
     nombreux
    1.60
     Cálculo
    1.50
     enregistré
    1.49
     verksam
    1.47
     conocimientos
    1.46
    issner
    1.45
     entendimento
    1.44
     moteurs
    1.43
     vuonna
    1.43
    Activations Density 0.001%

    No Known Activations