© 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. 148540
    Prev
    Next
    INDEX
    Explanations

    state transition

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

    logical operators or syntax

    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
    is
    0.48
    ましい
    0.48
    t
    0.47
     perceptible
    0.45
    bros
    0.44
     uncertainty
    0.43
    halogen
    0.43
    l
    0.42
     là
    0.41
     lobby
    0.41
    POSITIVE LOGITS
    শন
    0.52
    ज्ञान
    0.50
    Ꮒ
    0.50
    ༢
    0.49
    ных
    0.48
    וחות
    0.47
     ভূমি
    0.47
    టింగ్
    0.46
    蕖
    0.46
    ции
    0.45
    Activations Density 0.000%

    No Known Activations