© 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. 30205
    Prev
    Next
    INDEX
    Explanations

    types to

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

    parental rights, custody, view holds

    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
     Serv
    0.51
     Mont
    0.49
    ATO
    0.49
     Happ
    0.47
     Hartmann
    0.47
     ATP
    0.46
     Hawking
    0.46
    </h2>
    0.46
     Lazar
    0.46
     ATO
    0.46
    POSITIVE LOGITS
    ﻯ
    0.54
    繁殖
    0.49
    身體
    0.47
    ូម
    0.45
    laublich
    0.45
     փ
    0.45
    )、
    0.44
     मामूली
    0.44
    lsulfanyl
    0.44
    ntity
    0.44
    Activations Density 0.000%

    No Known Activations