© 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. 131164
    Prev
    Next
    INDEX
    Explanations

    band, September, drama, Until

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

    pronouns, fabric, pricing, deformation

    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
    Control
    0.52
    1
    0.51
    al
    0.49
    อ
    0.48
    UV
    0.48
     ஏ
    0.47
    ן
    0.47
    il
    0.46
    7
    0.46
    ↵
    0.46
    POSITIVE LOGITS
     eset
    0.51
     atmosfera
    0.50
    کل
    0.48
     stvar
    0.47
     concerned
    0.47
    न्दगी
    0.46
     tende
    0.45
    ويلة
    0.45
    сей
    0.45
     sociais
    0.44
    Activations Density 0.002%

    No Known Activations