© 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. 50219
    Prev
    Next
    INDEX
    Explanations

    float, floating

    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
    ,
    0.64
    ann
    0.54
    ard
    0.51
     \%,
    0.49
     համ
    0.49
    olding
    0.49
    apolis
    0.48
     étudier
    0.48
    anth
    0.47
    inas
    0.47
    POSITIVE LOGITS
     float
    1.05
     Float
    1.05
     FLOAT
    1.05
     floats
    0.94
     Floating
    0.92
    Floating
    0.87
    float
    0.86
    т
    0.84
    浮
    0.82
    FLOAT
    0.80
    Activations Density 0.008%

    No Known Activations