© 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. 31226
    Prev
    Next
    INDEX
    Explanations

    crisp air, mornings, food textures

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

    crisp lettuce, bacon, suits, fries

    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
    3
    0.56
    4
    0.53
     l
    0.50
     is
    0.50
     penetrates
    0.50
     are
    0.49
    iz
    0.49
    7
    0.49
    2
    0.48
    9
    0.48
    POSITIVE LOGITS
    вшая
    0.47
     μέρος
    0.47
    вших
    0.47
    ಡುವ
    0.46
     पटक
    0.46
    custList
    0.45
    能在
    0.44
     क्विंट
    0.43
    高于
    0.43
    क्रि
    0.43
    Activations Density 0.000%

    No Known Activations