© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68053
    Prev
    Next
    INDEX
    Explanations

    information in context

    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
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -2.09
     this
    -1.84
    :
    -1.44
     sostanze
    -1.39
     écoulé
    -1.37
     maupun
    -1.35
     rafraî
    -1.34
    Verweise
    -1.32
     tämä
    -1.32
     obligé
    -1.32
    POSITIVE LOGITS
     on
    2.31
     in
    2.02
     and
    1.95
     without
    1.60
     for
    1.58
     with
    1.43
     has
    1.35
     from
    1.34
    簡易
    1.33
    Scary
    1.30
    Activations Density 0.226%

    No Known Activations