© 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. 131953
    Prev
    Next
    INDEX
    Explanations

    numbers and references

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

    finding things that happen or are identified

    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
    מ
    0.46
     utenti
    0.45
     Bachchan
    0.43
     chuckled
    0.42
     Yao
    0.41
    ン
    0.41
    笑
    0.41
    Maharashtra
    0.41
     mistakenly
    0.41
     kunj
    0.41
    POSITIVE LOGITS
    
    0.47
    
    0.46
    visor
    0.45
     ಡಿ
    0.45
    
    0.45
    protein
    0.44
    颶
    0.44
    rimp
    0.43
    raised
    0.43
     डीएम
    0.43
    Activations Density 0.000%

    No Known Activations