© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    Focus, standing, minutes, water

    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
     ರೀತಿಯ
    0.47
    ၶ
    0.47
    deps
    0.45
     organisasi
    0.45
    catenin
    0.44
    ဴ
    0.44
     κάπο
    0.44
    Гц
    0.44
     poema
    0.43
    "+"|".
    0.43
    POSITIVE LOGITS
     daily
    0.55
    0.54
     reactivity
    0.52
     Energie
    0.50
     है
    0.48
     weight
    0.48
     belief
    0.47
     প্রতিদিন
    0.47
     finish
    0.46
     breath
    0.46
    Activations Density 0.008%

    No Known Activations