© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4303
    Prev
    Next
    INDEX
    Explanations

    size and quantity descriptors

    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_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
     costi
    0.38
    шими
    0.37
     JWT
    0.37
    ῇ
    0.37
    Coff
    0.37
    Attrition
    0.36
    Teams
    0.36
     Mél
    0.36
    धी
    0.35
    JWT
    0.35
    POSITIVE LOGITS
     (>
    1.45
     (<
    1.38
     (~
    1.38
     $(<
    1.25
     (\<
    1.13
    (<
    0.99
    (~
    0.88
     $(
    0.84
     (−
    0.82
     حوالي
    0.81
    Activations Density 0.950%

    No Known Activations