© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8439
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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_16k_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
    En
    0.52
    ภาษา
    0.51
     En
    0.49
    英语
    0.45
    エン
    0.41
    ホ
    0.41
     en
    0.40
    Engl
    0.40
    en
    0.39
    wait
    0.39
    POSITIVE LOGITS
     observations
    0.43
    恝
    0.41
    <unused2113>
    0.39
     powsta
    0.39
     Observations
    0.38
    জিওথেরাপি
    0.38
     "":
    0.38
     CELLS
    0.38
    Baj
    0.37
    \|
    0.37
    Activations Density 0.035%

    No Known Activations