© 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. 50111
    Prev
    Next
    INDEX
    Explanations

    patch merging

    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
    н
    0.59
     бес
    0.54
    Tiene
    0.51
    น
    0.51
    mq
    0.49
     ему
    0.49
     avea
    0.49
     Tiene
    0.48
     continúa
    0.48
     pierde
    0.48
    POSITIVE LOGITS
     Concise
    0.45
     Therapist
    0.45
     হাসপাত
    0.43
     Θ
    0.42
    梔
    0.41
     fringes
    0.40
     eigenvector
    0.40
     complacency
    0.40
     hinting
    0.39
    ్రహ
    0.38
    Activations Density 0.001%

    No Known Activations