© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46044
    Prev
    Next
    INDEX
    Explanations

    skills, keywords, details

    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
     normaal
    0.50
     réalisés
    0.47
    лянчук
    0.46
    ض
    0.46
    짧
    0.46
    شش
    0.45
     proposés
    0.44
     ancest
    0.44
     goût
    0.44
     vaginale
    0.43
    POSITIVE LOGITS
    ׃
    0.46
     ठहर
    0.44
    huana
    0.44
    boom
    0.44
     ת
    0.44
     ומ
    0.44
    ↵↵
    0.43
     boom
    0.43
    location
    0.43
    isOn
    0.43
    Activations Density 0.005%

    No Known Activations