© 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. 45974
    Prev
    Next
    INDEX
    Explanations

    What kind of

    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
    y
    0.68
    e
    0.59
     =
    0.56
    eine
    0.55
    {
    0.55
    i
    0.53
    ak
    0.52
     &=
    0.52
    Are
    0.52
    いて
    0.50
    POSITIVE LOGITS
     этим
    0.58
    this
    0.57
     этом
    0.56
     maximise
    0.56
    пя
    0.55
    assapi
    0.55
    igators
    0.55
     Himalayas
    0.55
     auditions
    0.54
     съем
    0.54
    Activations Density 0.098%

    No Known Activations