© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48526
    Prev
    Next
    INDEX
    Explanations

    characters having skills

    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_40_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
    抱
    0.55
    gini
    0.42
    🩷
    0.41
    𝙃
    0.40
     দার
    0.40
     সাহায
    0.40
    Фото
    0.39
    坝
    0.39
    TEXT
    0.39
    後の
    0.39
    POSITIVE LOGITS
     unions
    0.45
    ñal
    0.44
     कोर
    0.42
     なく
    0.42
    ermo
    0.41
     période
    0.41
     apple
    0.40
     windows
    0.40
     periods
    0.40
     plus
    0.38
    Activations Density 0.004%

    No Known Activations