© 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. 103100
    Prev
    Next
    INDEX
    Explanations

    you followed by action or state

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

    Fullscreen API

    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
    νο
    0.46
    rą
    0.45
     ခ
    0.45
     duyệt
    0.45
     ၁
    0.44
     gymnastics
    0.44
    Approval
    0.44
    דור
    0.44
    fibre
    0.44
    CheckingType
    0.44
    POSITIVE LOGITS
    0.45
     втори
    0.43
    propan
    0.42
    they
    0.41
    iado
    0.41
     сообщил
    0.40
    ussians
    0.40
    izantes
    0.40
    Katie
    0.40
    芒
    0.40
    Activations Density 0.000%

    No Known Activations