© 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. 107113
    Prev
    Next
    INDEX
    Explanations

    reaching out

    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
     IllegalArgument
    -0.78
    arques
    -0.77
     tagit
    -0.74
    音が
    -0.74
    pressor
    -0.73
    ֖
    -0.73
     epoca
    -0.71
     convento
    -0.71
     edades
    -0.71
     karyawan
    -0.71
    POSITIVE LOGITS
     out
    2.73
     outreach
    2.38
     reaching
    2.27
    reach
    2.23
     reach
    2.23
    reaching
    2.09
    Reach
    2.08
     Reach
    1.96
     reaches
    1.88
    reached
    1.81
    Activations Density 0.009%

    No Known Activations