© 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-262K
    7. 204787
    Prev
    Next
    INDEX
    Explanations

    removing filler words and phrases

    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
     perempt
    0.48
     região
    0.41
    ৌম
    0.41
     פע
    0.40
     мел
    0.40
     Django
    0.39
    ͠
    0.39
     kwenye
    0.39
     traitement
    0.38
    行動
    0.38
    POSITIVE LOGITS
    த்தால்
    0.52
    䐂
    0.48
    ucionales
    0.47
    טה
    0.46
     दृ
    0.46
     altas
    0.46
    лл
    0.46
    wl
    0.45
    ınca
    0.45
    MENT
    0.44
    Activations Density 0.001%

    No Known Activations