© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7339
    Prev
    Next
    INDEX
    Explanations

    voluntariness, time, issued, prices

    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_22_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
    weiß
    0.89
    endt
    0.84
     Neh
    0.81
    classmethod
    0.81
     मेयर
    0.81
    름
    0.78
     ascribe
    0.78
     长
    0.78
    entric
    0.76
    hljs
    0.75
    POSITIVE LOGITS
    sons
    1.13
    IVERS
    1.11
     movimentos
    1.08
     cuidadosamente
    1.00
     Barker
    1.00
     movimientos
    1.00
     Koval
    0.99
     Erfahr
    0.99
     mouvements
    0.99
     sons
    0.98
    Activations Density 0.000%

    No Known Activations