© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142484
    Prev
    Next
    INDEX
    Explanations

    New York City ramen

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

    2D and 3D terms

    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
     authoritative
    0.54
     conductivity
    0.51
     granularity
    0.51
     spectroscopic
    0.47
     spectroscopy
    0.47
     confidentiality
    0.44
     Č
    0.43
     useful
    0.43
     monitoring
    0.43
     uncountable
    0.43
    POSITIVE LOGITS
    Studio
    0.59
    萝
    0.55
     начале
    0.55
    成立于
    0.53
    現在は
    0.52
    Entrepreneur
    0.52
    徂
    0.52
    ្សែ
    0.52
    幵
    0.51
     Studio
    0.50
    Activations Density 0.000%

    No Known Activations