© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 45601
    Prev
    Next
    INDEX
    Explanations

    explaining vulnerability and covering special topics

    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
     OAuth
    0.54
     X
    0.51
     from
    0.50
     AUTH
    0.49
     stati
    0.46
     Ministry
    0.45
     assert
    0.44
     REAL
    0.44
     XYZ
    0.44
     EDGE
    0.44
    POSITIVE LOGITS
    city
    0.57
    Couldn
    0.50
    excluding
    0.50
    фр
    0.50
    chen
    0.48
    is
    0.47
    ၆
    0.46
     کررہ
    0.46
    ០
    0.46
     सुविधाएं
    0.46
    Activations Density 0.000%

    No Known Activations