© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15440
    Prev
    Next
    INDEX
    Explanations

    Addresses and locations

    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_31_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
    ugd
    0.43
     আশ্চর্য
    0.43
    valment
    0.42
    valmentaja
    0.42
    ⛷
    0.42
    alkeeper
    0.41
    Methylsulfanyl
    0.41
    校长
    0.41
    MathMarks
    0.41
    🕤
    0.40
    POSITIVE LOGITS
     resale
    0.54
     condos
    0.50
     prices
    0.47
     homes
    0.46
     residences
    0.46
     houses
    0.46
     condo
    0.45
     apartments
    0.44
     shopper
    0.44
     buyers
    0.44
    Activations Density 0.001%

    No Known Activations