© 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. 40-GEMMASCOPE-2-RES-65K
    7. 49599
    Prev
    Next
    INDEX
    Explanations

    financial and technical terms

    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
     free
    0.41
     hotter
    0.40
    $_
    0.39
     verrou
    0.39
     Free
    0.38
     metabolites
    0.38
     Dijon
    0.38
     आगरा
    0.38
     suspension
    0.37
     beau
    0.37
    POSITIVE LOGITS
    課題
    0.41
    Mira
    0.41
    omotive
    0.39
    globe
    0.39
    KIS
    0.39
    益
    0.39
    Mr
    0.37
    rieve
    0.36
    coes
    0.36
     Potenz
    0.36
    Activations Density 0.007%

    No Known Activations