© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5054
    Prev
    Next
    INDEX
    Explanations

    filler words like "like" and "well"

    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_16k_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
    olphe
    0.46
     Arrang
    0.44
     («
    0.43
     Recherches
    0.42
     Необходимо
    0.42
     (=
    0.42
     Bankr
    0.42
    supportsFocus
    0.42
     ([]
    0.41
     Два
    0.41
    POSITIVE LOGITS
    こんにちは
    0.49
    ,
    0.44
    Honestly
    0.43
     literalmente
    0.41
    %
    0.40
     honestly
    0.40
     percorso
    0.39
     ruta
    0.39
    ن
    0.38
    もちろん
    0.38
    Activations Density 0.106%

    No Known Activations