© 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. 138993
    Prev
    Next
    INDEX
    Explanations

    read or download epub mobi pdf

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

    condition or consequence

    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
     enseignants
    0.50
    blico
    0.48
     deceduto
    0.44
     hänen
    0.43
     komis
    0.43
    ἶ
    0.42
    lø
    0.41
     estadounidenses
    0.41
     ඔහුගේ
    0.41
    தேச
    0.41
    POSITIVE LOGITS
     እንዲሁ
    0.45
    Survival
    0.42
    မဟုတ်
    0.42
     전자
    0.41
    Dependency
    0.40
     সাপোর্ট
    0.40
     որ
    0.39
     Kindle
    0.39
    阅
    0.39
    ⇄
    0.39
    Activations Density 0.001%

    No Known Activations