© 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. 47223
    Prev
    Next
    INDEX
    Explanations

    projects, time, expression

    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
     ruins
    0.47
     இழ
    0.46
     അപകട
    0.45
     사람들이
    0.44
     injuries
    0.44
     덕
    0.43
    ങ്ങ
    0.42
     Isn
    0.42
     भक्तों
    0.42
     ages
    0.42
    POSITIVE LOGITS
    కుడు
    0.45
    up
    0.43
    el
    0.43
    esters
    0.42
    ennzeichnet
    0.42
    <0x80>
    0.41
    цент
    0.40
     جمله
    0.40
     Gemeins
    0.40
    veloppement
    0.39
    Activations Density 0.003%

    No Known Activations