© 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. 45851
    Prev
    Next
    INDEX
    Explanations

    try to learn

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

    to run, to eat, to induce

    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
    aginaw
    0.49
     কৰ
    0.48
    禮
    0.48
     ១
    0.45
    ／
    0.44
     크라운
    0.44
    Dictionaries
    0.44
     ／
    0.44
     Statistics
    0.43
     Probab
    0.43
    POSITIVE LOGITS
     mencoba
    0.49
     सीखना
    0.46
     poetic
    0.45
     tentativo
    0.44
    küm
    0.43
     sprinting
    0.43
     mulai
    0.43
     dokumen
    0.43
    stuk
    0.42
    抹
    0.42
    Activations Density 0.000%

    No Known Activations