© 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. 111828
    Prev
    Next
    INDEX
    Explanations

    linking concepts and actions

    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
    ול
    0.49
     과학
    0.49
    프
    0.48
    Dev
    0.46
    삭제
    0.46
    펭
    0.46
    모
    0.45
     Yuan
    0.45
     Zeitschr
    0.44
    Meng
    0.44
    POSITIVE LOGITS
    r
    0.45
    ão
    0.44
    localVarPath
    0.43
    áil
    0.40
     achter
    0.40
    oció
    0.40
     experiência
    0.39
    amera
    0.39
     licenc
    0.39
    ăți
    0.38
    Activations Density 0.004%

    No Known Activations