© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110214
    Prev
    Next
    INDEX
    Explanations

    precise timing, dioxide removal, taking commissions

    np_acts-logits-general · gemini-2.5-flash-lite

    choppy seas/strategically emit/affect wildlife

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    isocyanate
    0.54
    хие
    0.51
    и
    0.50
    чки
    0.48
     colegio
    0.48
     Бу
    0.46
     jardín
    0.45
     Bacillus
    0.45
     recorrido
    0.45
    !:
    0.45
    POSITIVE LOGITS
    rež
    0.45
     Offering
    0.44
     pozdě
    0.44
     Newborn
    0.44
     Pools
    0.43
     Unlike
    0.42
    燦
    0.41
    今後
    0.41
     Reservations
    0.41
     Proposals
    0.40
    Activations Density 0.000%

    No Known Activations