© 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. 125581
    Prev
    Next
    INDEX
    Explanations

    this is a

    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
    T
    0.51
    v
    0.50
    Figure
    0.46
    ن
    0.45
    Add
    0.44
    न
    0.44
    Note
    0.44
    Park
    0.43
    т
    0.43
    Ron
    0.43
    POSITIVE LOGITS
     ყველ
    0.60
     カラ
    0.56
     וי
    0.54
     จะ
    0.52
     Faites
    0.51
     biograf
    0.50
     環
    0.49
     شب
    0.48
     טי
    0.48
     ficando
    0.47
    Activations Density 0.002%

    No Known Activations