© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127999
    Prev
    Next
    INDEX
    Explanations

    legal, business, or technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    N
    -1.62
    L
    -1.44
    R
    -1.34
    P
    -1.33
    K
    -1.28
    Ｂ
    -1.26
    M
    -1.24
     berätt
    -1.22
    Література
    -1.22
    X
    -1.21
    POSITIVE LOGITS
    などが
    1.39
     favorece
    1.31
     and
    1.27
    ței
    1.27
    を含
    1.27
    を含む
    1.25
     favorecer
    1.24
    などを
    1.23
    affiche
    1.22
    ține
    1.21
    Activations Density 0.036%

    No Known Activations