© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151014
    Prev
    Next
    INDEX
    Explanations

    diverse expressions and data descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    important notes before you start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.50
     Head
    0.47
    ↵↵
    0.46
     Turn
    0.46
    珀
    0.45
     cr
    0.45
     Polyp
    0.44
     Norm
    0.43
     polych
    0.43
     Cold
    0.43
    POSITIVE LOGITS
     söyl
    0.48
     expresión
    0.48
     söyled
    0.46
     uitle
    0.46
     traducción
    0.44
    𝒗
    0.44
     integração
    0.43
     operaciones
    0.43
    еру
    0.43
     vervolgens
    0.43
    Activations Density 0.001%

    No Known Activations