© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 19987
    Prev
    Next
    INDEX
    Explanations

    coding and AI assistants

    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
    ЛЕ
    0.54
    לי
    0.43
    AMSUNG
    0.43
    ДУ
    0.42
    िमम
    0.42
    дена
    0.41
    드
    0.41
    ДИ
    0.40
    다
    0.40
    급
    0.39
    POSITIVE LOGITS
     facilite
    0.37
     birdseye
    0.37
    pliers
    0.37
    geom
    0.36
     again
    0.36
     collaborates
    0.36
    atics
    0.35
     baton
    0.34
    again
    0.33
     weer
    0.33
    Activations Density 0.081%

    No Known Activations