© 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. 139293
    Prev
    Next
    INDEX
    Explanations

    avoid filler words

    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
    。
    0.48
     any
    0.43
    if
    0.39
    any
    0.39
     absolutely
    0.39
     I
    0.38
    ’
    0.38
     ANY
    0.38
    ।
    0.38
     anytime
    0.38
    POSITIVE LOGITS
     incluido
    0.46
     vytvá
    0.45
     incluidas
    0.45
     successively
    0.45
     culmin
    0.44
     várias
    0.44
     yüzden
    0.44
     culminated
    0.44
     successivement
    0.44
     algéb
    0.43
    Activations Density 0.010%

    No Known Activations