© 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. 176227
    Prev
    Next
    INDEX
    Explanations

    parking duration and cost

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

    user prompts

    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
    徥
    0.59
    ificance
    0.50
     alphabet
    0.48
     buttermilk
    0.47
     పు
    0.47
     வருவத
    0.45
    ifred
    0.44
     த
    0.44
     ما
    0.43
    фта
    0.43
    POSITIVE LOGITS
     gid
    0.54
     calles
    0.47
     soutenir
    0.46
     Chad
    0.46
     AO
    0.46
     guste
    0.46
     réduire
    0.46
     chad
    0.45
     justamente
    0.45
     poprzez
    0.45
    Activations Density 0.001%

    No Known Activations