© 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. 221702
    Prev
    Next
    INDEX
    Explanations

    tax free

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

    self-referential phrases

    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
    "
    0.49
     re
    0.45
    ?
    0.44
     `
    0.44
    De
    0.44
     fling
    0.44
     reigning
    0.43
     push
    0.41
     แท
    0.41
     helicopter
    0.41
    POSITIVE LOGITS
    каз
    0.54
    ఞ
    0.53
    說明
    0.53
    簽證
    0.52
     Inicio
    0.51
    ாடு
    0.51
    sourceEncoding
    0.50
     اكس
    0.50
     Partie
    0.50
     Gespräch
    0.49
    Activations Density 0.000%

    No Known Activations