© 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. 192841
    Prev
    Next
    INDEX
    Explanations

    speculative designs and contracts

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

    technical terms or entities

    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
    Negative Logits
     ቅ
    0.51
    ਟ
    0.49
    䁂
    0.49
    और
    0.46
    ank
    0.45
    反
    0.45
    Об
    0.45
    ಪ
    0.45
    龰
    0.44
    humidité
    0.43
    POSITIVE LOGITS
     speculative
    0.54
     fea
    0.49
     spans
    0.48
     design
    0.47
     raff
    0.46
     asparagus
    0.46
     proj
    0.46
     payable
    0.45
     présent
    0.45
     slabs
    0.45
    Activations Density 0.001%

    No Known Activations