© 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. 192391
    Prev
    Next
    INDEX
    Explanations

    numbers and IPT

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

    customization placeholders or bracketed instructions

    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
    velocity
    0.49
    ition
    0.47
    union
    0.46
    ?
    0.46
    合
    0.46
    indirect
    0.45
    VE
    0.44
    vstack
    0.44
    扇
    0.44
    oil
    0.43
    POSITIVE LOGITS
     Dienst
    0.56
    dienst
    0.54
     ingenu
    0.52
     Serviços
    0.52
     Número
    0.51
    larla
    0.49
     número
    0.48
     estás
    0.48
     asistente
    0.48
     IPT
    0.48
    Activations Density 0.000%

    No Known Activations