© 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. 143239
    Prev
    Next
    INDEX
    Explanations

    explaining things

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

    laws and specific circumstances

    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
    ുവരി
    0.45
    IONS
    0.45
    ்டோ
    0.43
    iprofloxacin
    0.43
     HUN
    0.43
     स्टेशनों
    0.43
    ┝
    0.43
    АН
    0.42
    াজার
    0.41
    ло
    0.40
    POSITIVE LOGITS
     apport
    0.54
     टेली
    0.50
     νο
    0.49
    จะต้อง
    0.48
     Teles
    0.48
     מד
    0.48
     reorgan
    0.48
    dokka
    0.47
     つ
    0.47
    peut
    0.46
    Activations Density 0.000%

    No Known Activations