© 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-65K
    7. 16191
    Prev
    Next
    INDEX
    Explanations

    website addresses

    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
     (
    0.36
     YouTube
    0.33
     PayPal
    0.32
     <
    0.32
    4
    0.31
     may
    0.31
     Facebook
    0.31
      
    0.30
    了吗
    0.30
    6
    0.30
    POSITIVE LOGITS
     halides
    0.34
     கொண்டனர்
    0.33
    ಡುವ
    0.32
    咅
    0.32
    łada
    0.32
     srcs
    0.31
    hygine
    0.31
     protons
    0.31
     ecmaVersion
    0.31
     ascertaining
    0.30
    Activations Density 0.176%

    No Known Activations