© 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. 97977
    Prev
    Next
    INDEX
    Explanations

    noun phrases

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

    bioluminescent bloom or gradle dependencies

    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
     megaphone
    0.47
    ৯
    0.47
    🅱
    0.47
    ArrowToggle
    0.46
    เพื่อน
    0.46
    ๘
    0.46
    ění
    0.44
    ৩
    0.44
     buildFor
    0.44
    ๓
    0.43
    POSITIVE LOGITS
     Una
    0.50
     Obl
    0.48
     act
    0.48
     Investig
    0.48
     Had
    0.47
     Beasts
    0.47
     had
    0.46
     hadn
    0.46
    Ott
    0.45
     Laid
    0.45
    Activations Density 0.000%

    No Known Activations