© 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. 88227
    Prev
    Next
    INDEX
    Explanations

    specific units or quantities

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

    introducing concepts or states

    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
     terkait
    0.47
    앰
    0.45
    тельстве
    0.45
    oarece
    0.43
    Loved
    0.43
    ributed
    0.43
    뗄
    0.42
    ಟಿ
    0.41
    کان
    0.41
     całość
    0.41
    POSITIVE LOGITS
     knn
    0.50
    anche
    0.48
     অবস্থ
    0.44
     kommt
    0.43
     splendor
    0.43
     decim
    0.43
     inund
    0.42
    ر
    0.42
     অস্ত্র
    0.42
     snapper
    0.42
    Activations Density 0.001%

    No Known Activations