© 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. 147734
    Prev
    Next
    INDEX
    Explanations

    sustainable practices

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

    royal, purity, scientific, space

    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
    _
    0.60
     subnet
    0.49
     rozs
    0.47
     chats
    0.47
     Sudan
    0.46
     budete
    0.46
     alike
    0.45
    Ả
    0.45
     is
    0.45
     afric
    0.45
    POSITIVE LOGITS
    ㌔
    0.42
     пробу
    0.41
     পর্যায়ের
    0.41
    fring
    0.41
    ہرست
    0.41
    ادی
    0.41
    FloatField
    0.41
    getRuntime
    0.40
    दायक
    0.40
    ]*(
    0.40
    Activations Density 0.001%

    No Known Activations