© 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. 217816
    Prev
    Next
    INDEX
    Explanations

    map one

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

    trap air, memory accordingly, event in

    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
    ​,
    0.55
     Assessing
    0.55
    정책
    0.52
    ፧
    0.51
     lLoginID
    0.50
    㳒
    0.49
     блоков
    0.48
     України
    0.47
     рэгістрацыі
    0.47
     POLICY
    0.47
    POSITIVE LOGITS
     canal
    0.49
     one
    0.49
     recherche
    0.47
     crab
    0.47
     waiter
    0.47
     sweetly
    0.47
    verd
    0.46
    喜
    0.46
    U
    0.45
    Gi
    0.45
    Activations Density 0.001%

    No Known Activations