© 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. 14414
    Prev
    Next
    INDEX
    Explanations

    less dry

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

    food and cooking descriptions

    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
    供应链
    0.89
    缡
    0.77
    鐒
    0.73
    鳕
    0.72
    螫
    0.71
    玧
    0.71
    区块
    0.70
    谘
    0.70
    屶
    0.68
    铉
    0.68
    POSITIVE LOGITS
     Chinese
    0.74
     chinese
    0.66
     little
    0.63
     con
    0.61
     que
    0.60
     steamed
    0.60
     t
    0.59
     rheumatism
    0.59
     scanty
    0.59
     it
    0.58
    Activations Density 0.026%

    No Known Activations