© 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. 31-GEMMASCOPE-2-RES-65K
    7. 30176
    Prev
    Next
    INDEX
    Explanations

    dart code imports

    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_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
     organiques
    0.43
     desi
    0.42
     bashing
    0.41
    ("")]
    0.41
     leis
    0.40
     essentielles
    0.39
    (!)
    0.38
     கேட்டு
    0.38
    digo
    0.37
    τίας
    0.37
    POSITIVE LOGITS
     নম
    0.45
     seyd
    0.44
    نام
    0.44
    ianz
    0.42
    "
    0.42
     Milch
    0.41
    আমার
    0.39
    的反
    0.39
    쇼
    0.39
    TextField
    0.38
    Activations Density 0.007%

    No Known Activations