© 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-65K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    ('
    0.24
    ޢ
    0.24
     nondegenerate
    0.23
     إليه
    0.21
    umbers
    0.21
     furtherance
    0.21
     shameless
    0.21
     (),
    0.21
     muted
    0.20
    اعدة
    0.20
    POSITIVE LOGITS
     (((
    0.24
    (((
    0.22
    =((
    0.21
    Get
    0.21
    +(\
    0.21
    त्रेयी
    0.21
    ((\
    0.20
     আকাশের
    0.20
     Get
    0.20
    {(
    0.20
    Activations Density 0.205%

    No Known Activations