© 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. 114228
    Prev
    Next
    INDEX
    Explanations

    speech continuations

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

    consultants and people

    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
    Traité
    0.49
    الی
    0.47
    InBuffer
    0.47
    TextureAsset
    0.47
    䖝
    0.45
    timevals
    0.45
    ENN
    0.44
    (/^
    0.44
     двадцать
    0.44
    ანს
    0.44
    POSITIVE LOGITS
     run
    0.50
     attack
    0.50
     it
    0.47
     extrac
    0.47
     SPEED
    0.46
     increase
    0.46
     apple
    0.46
     avoided
    0.46
    ພວກເຮ
    0.46
     implement
    0.45
    Activations Density 0.000%

    No Known Activations