© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6785
    Prev
    Next
    INDEX
    Explanations

    reach out for help

    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
     ";"
    0.26
     crepe
    0.26
     upwards
    0.25
     linéaire
    0.25
     linguaggio
    0.25
    x
    0.25
     المشروع
    0.25
     매우
    0.25
    xb
    0.25
     similaire
    0.25
    POSITIVE LOGITS
    ’
    0.30
    需
    0.29
    ਾ
    0.28
    де
    0.28
    '
    0.28
    各種
    0.28
    कर
    0.27
    يا
    0.26
    ه
    0.26
    ان
    0.26
    Activations Density 0.026%

    No Known Activations