© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128177
    Prev
    Next
    INDEX
    Explanations

    versions at

    np_acts-logits-general · gemini-2.5-flash-lite

    emulsifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     სან
    0.46
    registration
    0.44
     connotation
    0.41
    ᄂ
    0.41
     บ
    0.41
     inutile
    0.40
    早く
    0.40
    B
    0.40
    하기도
    0.40
    ו
    0.40
    POSITIVE LOGITS
     renewing
    0.43
     =)
    0.43
    瓈
    0.43
    为人
    0.41
    当我
    0.41
     தமிழரசுக்
    0.40
     lessened
    0.40
     simpel
    0.40
     चेंजेस
    0.40
     cuyos
    0.39
    Activations Density 0.000%

    No Known Activations