© 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. 40-GEMMASCOPE-2-RES-65K
    7. 507
    Prev
    Next
    INDEX
    Explanations

    PowerQuery code definitions and narrative reports

    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_40_width_65k_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
     TYPE
    0.45
    त्रेयी
    0.43
     senyawa
    0.42
    Ⲏ
    0.41
     comté
    0.40
    ោម
    0.40
     tubules
    0.40
     Kemal
    0.40
     Donec
    0.39
     trycatch
    0.39
    POSITIVE LOGITS
    langle
    0.36
     Experiment
    0.36
    protect
    0.36
    וּ
    0.36
     ź
    0.35
    usin
    0.35
     Baseline
    0.35
    ស្ល
    0.34
     出
    0.34
    related
    0.34
    Activations Density 0.003%

    No Known Activations