© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129171
    Prev
    Next
    INDEX
    Explanations

    What, Why, Jorge

    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
     in
    -1.35
    0
    -1.21
     Linie
    -1.21
     –
    -1.20
    leyen
    -1.16
    ForRow
    -1.15
    /</
    -1.15
    datable
    -1.14
     which
    -1.13
    artment
    -1.12
    POSITIVE LOGITS
     deberán
    1.30
    迨
    1.29
     coraggio
    1.25
    relenting
    1.25
     _________
    1.24
     recklessly
    1.23
     dettagli
    1.22
     viață
    1.22
    selecting
    1.20
     prides
    1.20
    Activations Density 0.004%

    No Known Activations