© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33238
    Prev
    Next
    INDEX
    Explanations

    change in amount or percentage

    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
    வீன
    0.43
    بتدي
    0.42
    ιον
    0.39
     vicinity
    0.39
    apati
    0.38
    实力
    0.38
     چی
    0.38
    炘
    0.38
    实施
    0.37
    Changing
    0.37
    POSITIVE LOGITS
     increase
    1.01
     decrease
    0.92
     difference
    0.92
    increase
    0.90
     loss
    0.89
     reduction
    0.88
     incremento
    0.87
     reductions
    0.86
     improvement
    0.84
     deviation
    0.84
    Activations Density 0.043%

    No Known Activations