© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71570
    Prev
    Next
    INDEX
    Explanations

    statistics of

    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
     doubtless
    -2.44
    坶
    -2.42
    能在
    -2.36
    nambuco
    -2.36
     intrepid
    -2.33
     astute
    -2.30
    t
    -2.22
    泺
    -2.22
     was
    -2.20
    是在
    -2.19
    POSITIVE LOGITS
    ”;
    3.08
    ”:
    2.92
    .
    2.89
     Anordnung
    2.56
    ”،
    2.55
     \
    2.50
    “
    2.50
     erwähnten
    2.45
    нимание
    2.42
    ではでは
    2.42
    Activations Density 0.007%

    No Known Activations