© 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. 41417
    Prev
    Next
    INDEX
    Explanations

    communication and reports

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

    discussing freedoms and costs

    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
     lakini
    0.41
     אבל
    0.38
     nhưng
    0.37
     Và
    0.36
     لكن
    0.34
     থাকলেও
    0.34
    %.
    0.34
    ությունը
    0.34
     இருந்தாலும்
    0.34
     Feels
    0.34
    POSITIVE LOGITS
    如何
    0.47
     bagaimana
    0.45
     විසින්
    0.44
     如何
    0.44
     hvordan
    0.43
     addNew
    0.40
     단순히
    0.40
     kako
    0.39
    
    0.38
     olyan
    0.38
    Activations Density 0.069%

    No Known Activations