© 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. 155420
    Prev
    Next
    INDEX
    Explanations

    participants, providers

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

    phrases that negate or describe limitations

    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
    لا
    0.48
    רו
    0.48
     standard
    0.45
    לא
    0.44
    2
    0.43
     primary
    0.42
    פי
    0.42
     relative
    0.41
    מר
    0.41
    v
    0.41
    POSITIVE LOGITS
    anu
    0.54
     falou
    0.52
    кура
    0.52
    
    0.50
     شرطونه
    0.50
    憸
    0.50
     gespre
    0.49
    attered
    0.49
     компания
    0.49
    ະພັນ
    0.48
    Activations Density 0.000%

    No Known Activations