© 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. 115934
    Prev
    Next
    INDEX
    Explanations

    Retrieved dates

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

    inputs and user data

    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
    十八
    0.46
    ̓
    0.45
    работки
    0.44
    راع
    0.42
     टाइम
    0.38
    ocking
    0.37
     gimnas
    0.37
    ̈́
    0.37
     cache
    0.37
     সম্বন্ধে
    0.37
    POSITIVE LOGITS
    Meri
    0.38
     erit
    0.37
     회
    0.37
     കള
    0.37
     chúc
    0.37
     hans
    0.37
     Catawiki
    0.37
     ContentValues
    0.36
    ëve
    0.36
     처
    0.36
    Activations Density 0.109%

    No Known Activations