© 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. 2127
    Prev
    Next
    INDEX
    Explanations

    definitions and clauses

    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
    銠
    0.40
     Fransiya
    0.38
    ठभे
    0.38
    (&:
    0.38
     váy
    0.37
    
    0.37
    𝔞
    0.37
     pâte
    0.36
    脿
    0.36
    ához
    0.36
    POSITIVE LOGITS
    t
    0.43
     Sever
    0.42
     non
    0.41
     Hu
    0.40
    PO
    0.39
     cancellation
    0.39
    AI
    0.38
     If
    0.38
     may
    0.38
    Min
    0.37
    Activations Density 0.000%

    No Known Activations