© 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. 61904
    Prev
    Next
    INDEX
    Explanations

    ties, cooked, perfect, any, problem, war, discount

    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
    اون
    0.42
     AND
    0.42
    מע
    0.41
     않으면
    0.40
    스
    0.40
    ৯
    0.40
    ете
    0.39
    ת
    0.39
     Произ
    0.39
    ешь
    0.38
    POSITIVE LOGITS
     critica
    0.44
     fats
    0.41
     spectroscopic
    0.41
     yattha
    0.41
     therein
    0.40
    Globalization
    0.39
     intramolecular
    0.39
    Weyl
    0.38
     bicarbon
    0.38
    getCQL
    0.38
    Activations Density 0.001%

    No Known Activations