© 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. 169176
    Prev
    Next
    INDEX
    Explanations

    shortened words and abbreviations

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

    spoken Dravidian languages

    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
     nyní
    0.45
     neder
    0.42
     konfl
    0.41
    💑
    0.41
    🏄
    0.40
    ല്ലോ
    0.40
     restitution
    0.40
     mö
    0.39
     mycel
    0.39
     trá
    0.39
    POSITIVE LOGITS
     vaccines
    0.49
     workday
    0.49
    buyers
    0.48
    getCount
    0.46
     avevano
    0.45
     bartenders
    0.44
     used
    0.44
    হ
    0.44
    頎
    0.44
    used
    0.44
    Activations Density 0.005%

    No Known Activations