© 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. 69065
    Prev
    Next
    INDEX
    Explanations

    actions followed by their objects or conditions

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

    absorbed by, rings

    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
    χι
    0.42
    ли
    0.41
    ус
    0.41
    լ
    0.41
     accurately
    0.39
     Sé
    0.39
     ungew
    0.39
    ኪ
    0.39
     amphibians
    0.38
     plumb
    0.38
    POSITIVE LOGITS
     พวก
    0.50
     випадку
    0.49
    ದ್ದರಿಂದ
    0.48
     আজকে
    0.48
     обсу
    0.47
    valuer
    0.46
    พวก
    0.46
     เวลา
    0.45
     প্রত্যেক
    0.44
     चार्ज
    0.44
    Activations Density 0.001%

    No Known Activations