© 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. 211932
    Prev
    Next
    INDEX
    Explanations

    warranty provision

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

    air flow restricts

    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
    ayette
    0.48
    ἥ
    0.48
     marchio
    0.45
     üy
    0.44
    amber
    0.44
    ulong
    0.43
    YC
    0.42
     centro
    0.42
    ંદ્ર
    0.42
    鿢
    0.42
    POSITIVE LOGITS
    ی
    0.57
     impactful
    0.46
    ائم
    0.45
    الا
    0.45
    ოველ
    0.45
    oners
    0.45
     Output
    0.44
     Dinner
    0.44
     Consequently
    0.44
     impeccable
    0.44
    Activations Density 0.001%

    No Known Activations