© 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. 18950
    Prev
    Next
    INDEX
    Explanations

    checking conditions or states

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

    checking existence or conditions

    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
     ალ
    0.49
     сто
    0.46
    贈り物
    0.46
     מל
    0.45
    脩
    0.44
    ろ
    0.44
     ہمیشہ
    0.44
    瀘
    0.44
    ด
    0.43
    ан
    0.42
    POSITIVE LOGITS
     !=
    0.86
    hasClass
    0.80
     není
    0.80
     ikke
    0.79
     nėra
    0.79
     नहीं
    0.76
     exista
    0.76
    hasOwnProperty
    0.73
     είναι
    0.73
     isn
    0.73
    Activations Density 0.002%

    No Known Activations