© 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. 41-GEMMASCOPE-2-RES-262K
    4. 62428
    Prev
    Next
    INDEX
    Explanations

    safety reporting

    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_all/layer_41_width_262k_l0_big
    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
    טים
    0.45
    Correo
    0.44
    không
    0.44
    。。。
    0.43
    nocześnie
    0.43
    ależ
    0.42
    camiseta
    0.42
    ổ
    0.42
    gmail
    0.42
    émi
    0.41
    POSITIVE LOGITS
     these
    0.51
     array
    0.49
     plane
    0.46
     capability
    0.45
     vector
    0.43
     transpose
    0.43
     thermal
    0.43
     transposed
    0.43
     chi
    0.42
     thirds
    0.42
    Activations Density 0.000%

    No Known Activations