© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8898
    Prev
    Next
    INDEX
    Explanations

    intended for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     represented
    0.40
    yal
    0.39
     machining
    0.38
     carved
    0.37
     where
    0.37
    Built
    0.37
     carving
    0.36
    <>
    0.36
    Availability
    0.36
    represented
    0.35
    POSITIVE LOGITS
     destinés
    1.09
     destined
    1.03
     destinée
    0.95
     destiné
    0.92
     destinado
    0.90
     destinados
    0.85
     destinada
    0.84
     destin
    0.80
     предназна
    0.80
     предназначен
    0.75
    Activations Density 0.218%

    No Known Activations