© 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. 137602
    Prev
    Next
    INDEX
    Explanations

    costs and requirements

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

    ** or that

    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
    Confident
    0.47
     перевод
    0.44
    ]->
    0.44
     confident
    0.43
     certos
    0.43
     cardiomyocytes
    0.42
     நடக்க
    0.42
     deduce
    0.41
    their
    0.41
    PLY
    0.41
    POSITIVE LOGITS
    ล
    0.50
     τ
    0.48
    κ
    0.46
    क्स
    0.46
     νε
    0.45
     เหมาะ
    0.45
    क्
    0.44
     キッズ
    0.44
     oily
    0.43
     Patrol
    0.43
    Activations Density 0.000%

    No Known Activations