© 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. 78706
    Prev
    Next
    INDEX
    Explanations

    point out information

    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
     monde
    -0.88
    accharides
    -0.88
     Aguas
    -0.87
    KeySpec
    -0.87
     gelingt
    -0.82
     zonas
    -0.82
    骓
    -0.82
     Aceh
    -0.81
     prision
    -0.81
    ﾛ
    -0.80
    POSITIVE LOGITS
     out
    1.84
     to
    1.50
     towards
    1.09
     toward
    0.96
     fingers
    0.96
     移动
    0.81
    RetVal
    0.80
    towards
    0.79
     discutir
    0.79
     that
    0.78
    Activations Density 0.006%

    No Known Activations