© 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. 34-GEMMASCOPE-RES-131K
    7. 109059
    Prev
    Next
    INDEX
    Explanations

    java package declarations

    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
     despite
    -1.16
     because
    -0.97
     then
    -0.96
     our
    -0.93
     even
    -0.92
     Despite
    -0.90
     first
    -0.90
    Despite
    -0.88
     trotz
    -0.87
     apesar
    -0.87
    POSITIVE LOGITS
    readonly
    1.77
     readonly
    1.51
    }[
    1.12
     [
    1.08
    ():
    0.99
    wiet
    0.98
    /**
    0.98
    /**
    0.96
    位於
    0.94
    rée
    0.94
    Activations Density 0.011%

    No Known Activations