© 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. 49096
    Prev
    Next
    INDEX
    Explanations

    categories and 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_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
     hormones
    0.41
     casual
    0.40
     trivia
    0.39
     random
    0.38
     u
    0.38
     ile
    0.37
     joined
    0.37
     di
    0.37
     internationally
    0.37
     casually
    0.37
    POSITIVE LOGITS
    ➝
    0.52
     Themes
    0.47
    Concepts
    0.44
     Concepts
    0.43
    Themes
    0.43
    ukam
    0.43
    Theory
    0.41
     Seguridad
    0.40
    Parse
    0.40
    গ্ত
    0.39
    Activations Density 0.001%

    No Known Activations