© 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. 162459
    Prev
    Next
    INDEX
    Explanations

    pale art

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

    conditional statements and descriptions

    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
    ϴ
    0.46
     μου
    0.45
    
    0.44
    ɸ
    0.44
    敘
    0.42
    
    0.42
    設立
    0.41
     gepub
    0.41
    WHAT
    0.40
     Są
    0.40
    POSITIVE LOGITS
     দুর
    0.47
     extend
    0.46
     Matters
    0.46
    িপ
    0.45
    کتر
    0.45
     Mahmud
    0.45
     consciente
    0.45
    ，
    0.44
    会
    0.43
     matters
    0.42
    Activations Density 0.000%

    No Known Activations