© 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. 201998
    Prev
    Next
    INDEX
    Explanations

    average progress

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

    crucial information

    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
     බව
    0.50
     আগমন
    0.49
     ದು
    0.47
     الغ
    0.47
     Λ
    0.47
     Calyce
    0.47
     দ্ব
    0.46
     اكيد
    0.46
     লোভ
    0.46
     കൂടുത
    0.46
    POSITIVE LOGITS
    \
    0.49
    שׁ
    0.48
     sentence
    0.47
     target
    0.43
    یسر
    0.43
    ः
    0.43
     rive
    0.41
    綫
    0.41
    ם
    0.41
    sentence
    0.40
    Activations Density 0.001%

    No Known Activations