© 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. 97412
    Prev
    Next
    INDEX
    Explanations

    coverage is, attempt ., site

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

    AWS CLI config

    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
    ס
    0.52
    REEN
    0.47
    ן
    0.47
     drei
    0.46
     zwei
    0.46
     eup
    0.46
    utter
    0.45
     ו
    0.45
    ন্ধ
    0.44
    था
    0.44
    POSITIVE LOGITS
     मछ
    0.53
    
    0.45
     infiltration
    0.45
    入場
    0.45
     domic
    0.44
    リューション
    0.44
     🤔
    0.44
     (__
    0.43
     BSData
    0.43
     τῶν
    0.43
    Activations Density 0.000%

    No Known Activations