© 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. 99820
    Prev
    Next
    INDEX
    Explanations

    artist likes to

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

    sophisticated predictive machines

    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
     պ
    0.52
     گو
    0.49
     თ
    0.48
    簧
    0.47
     chron
    0.45
     করিল
    0.45
     มี
    0.44
     করিতেছে
    0.44
     球
    0.43
     Oncol
    0.42
    POSITIVE LOGITS
    );">
    0.54
    स्ड
    0.47
    astype
    0.47
     vengeance
    0.47
    또
    0.46
     புகை
    0.46
    ){}
    0.46
    moustache
    0.46
     campers
    0.46
     takers
    0.45
    Activations Density 0.001%

    No Known Activations