© 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. 16-GEMMASCOPE-2-RES-262K
    7. 104539
    Prev
    Next
    INDEX
    Explanations

    original title or purpose

    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_16_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
     isn
    0.53
    یتے
    0.51
     we
    0.50
     tellement
    0.49
     আমরা
    0.47
    আমরা
    0.47
     shrinking
    0.45
    잔
    0.44
     let
    0.44
    殘
    0.44
    POSITIVE LOGITS
    EnglishMarks
    0.53
    ahul
    0.50
     начала
    0.47
    មូល
    0.46
    MathMarks
    0.46
    辍
    0.46
    ApiCalls
    0.46
    ;}
    0.46
    lán
    0.46
    следование
    0.46
    Activations Density 0.001%

    No Known Activations