© 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. 79743
    Prev
    Next
    INDEX
    Explanations

    predicting next action or outcome

    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
     guests
    0.56
    _
    0.50
    ’
    0.49
     councils
    0.47
     councillors
    0.47
     continue
    0.46
     returned
    0.45
     duties
    0.45
    ounces
    0.45
     unsold
    0.45
    POSITIVE LOGITS
     페
    0.56
     제작
    0.51
     평가
    0.49
     едно
    0.49
     선택
    0.47
     스
    0.47
     드
    0.47
    ніка
    0.47
     фестива
    0.47
     버튼
    0.46
    Activations Density 0.001%

    No Known Activations