© 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. 10-GEMMASCOPE-RES-131K
    7. 22728
    Prev
    Next
    INDEX
    Explanations

    for you, for me, for us

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    琊
    -1.55
     for
    -1.55
     terjadi
    -1.52
    きちんと
    -1.46
    できれば
    -1.45
    𝟒
    -1.40
     the
    -1.40
    良く
    -1.31
    IQUES
    -1.31
    ují
    -1.27
    POSITIVE LOGITS
     thing
    1.72
    ();
    1.64
    ፝
    1.55
    СЯ
    1.55
     lasse
    1.55
    ſu
    1.54
    by
    1.52
    凱
    1.52
    providedIn
    1.49
     Anfitrión
    1.49
    Activations Density 0.016%

    No Known Activations