© 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. 34-GEMMASCOPE-RES-131K
    7. 48671
    Prev
    Next
    INDEX
    Explanations

    numbered list items

    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_34/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
    Both
    -1.34
    With
    -1.32
    Three
    -1.30
    维基
    -1.28
    Because
    -1.27
    Shortly
    -1.23
    Using
    -1.22
    Even
    -1.22
    Despite
    -1.22
     in
    -1.20
    POSITIVE LOGITS
     horrid
    1.19
     ornate
    1.18
    对着
    1.14
    があり
    1.14
     marvelous
    1.13
     colossal
    1.12
     fervent
    1.12
     wondrous
    1.12
     quintessential
    1.09
     horrible
    1.08
    Activations Density 0.002%

    No Known Activations