© 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. 30193
    Prev
    Next
    INDEX
    Explanations

    city rides

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

    encrypt Allah teams

    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
    án
    0.55
    ång
    0.52
    Ν
    0.52
    ui
    0.51
    getBy
    0.51
    giveness
    0.50
    阃
    0.49
    ⑹
    0.49
    ics
    0.49
    uctance
    0.48
    POSITIVE LOGITS
     Kier
    0.53
     Luna
    0.52
     Star
    0.50
     Therapie
    0.50
     Fuente
    0.49
     calef
    0.48
     Aqui
    0.48
     compuesto
    0.48
    אל
    0.48
     embellished
    0.48
    Activations Density 0.000%

    No Known Activations