© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6653
    Prev
    Next
    INDEX
    Explanations

    inspiration and origin

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

    origin or impetus

    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_53_width_65k_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
    少なくとも
    0.55
    Depending
    0.51
     অন্তত
    0.49
    Reserved
    0.46
     Presumably
    0.44
     আগামীকাল
    0.44
     Depending
    0.44
    🖕
    0.44
    Preferred
    0.43
     almeno
    0.43
    POSITIVE LOGITS
     inspiration
    1.13
    きっかけ
    1.05
     inspirations
    1.02
     inspired
    0.99
     idea
    0.94
     Idee
    0.93
     идея
    0.93
     inspiración
    0.92
     inspirado
    0.92
    偶然
    0.91
    Activations Density 0.219%

    No Known Activations