© 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. 12561
    Prev
    Next
    INDEX
    Explanations

    business production efficiency

    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
    allax
    2.21
    ᆷ
    2.18
    νή
    2.01
     സ്വാ
    1.95
    ᾿
    1.92
    Flipper
    1.92
     infile
    1.90
     ragion
    1.90
     richiest
    1.89
    呯
    1.85
    POSITIVE LOGITS
    崁
    1.95
    tri
    1.90
    ates
    1.88
    ು
    1.85
    uxi
    1.81
     Nxe
    1.81
    dern
    1.80
     bosom
    1.76
    der
    1.74
    trip
    1.73
    Activations Density 0.455%

    No Known Activations