© 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. 31-GEMMASCOPE-2-RES-65K
    7. 54050
    Prev
    Next
    INDEX
    Explanations

    moving artwork, wireless technology, running mate

    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_31_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
     RA
    0.43
     FA
    0.42
     अंदा
    0.40
    WING
    0.40
    <unused226>
    0.40
     আরও
    0.39
     Eagle
    0.38
     Niall
    0.38
     BE
    0.38
    корд
    0.38
    POSITIVE LOGITS
    carbam
    0.52
    ﻳ
    0.48
    emptyset
    0.46
     corticoster
    0.46
     ಸ್ಥ
    0.45
     necrotic
    0.45
    routing
    0.44
    seleccion
    0.43
    selected
    0.42
    eto
    0.42
    Activations Density 0.000%

    No Known Activations