© 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. 12261
    Prev
    Next
    INDEX
    Explanations

    water, dry, liquids

    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
    IntVar
    1.28
     einschließlich
    1.16
    IVACON
    1.15
     schweren
    1.15
    Փ
    1.15
    艰
    1.14
     gefähr
    1.13
     Saraj
    1.13
     schwierig
    1.13
     života
    1.12
    POSITIVE LOGITS
     posits
    1.15
    as
    1.04
    webs
    1.03
    h
    0.98
     blogs
    0.97
     notes
    0.94
    sec
    0.93
    which
    0.90
     boxes
    0.90
     Blogs
    0.89
    Activations Density 0.000%

    No Known Activations