© 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-262K
    7. 23262
    Prev
    Next
    INDEX
    Explanations

    plotting code and real-world examples

    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_262k_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
    inserts
    0.43
    Minimum
    0.40
     magasins
    0.39
     chimique
    0.38
     Dign
    0.38
    씬
    0.38
    Gal
    0.36
     يرد
    0.36
    Ց
    0.35
    パール
    0.35
    POSITIVE LOGITS
     porosity
    0.40
     चल
    0.39
    recursive
    0.38
     '-':
    0.38
     NLP
    0.37
     Mav
    0.37
     VL
    0.36
     chaos
    0.36
     recursively
    0.36
     BERT
    0.35
    Activations Density 0.000%

    No Known Activations