© 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. 63386
    Prev
    Next
    INDEX
    Explanations

    names starting with Kod or Jod

    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
    imy
    -0.77
    شارة
    -0.74
    пто
    -0.73
    ַ
    -0.71
     mali
    -0.70
    kok
    -0.69
     chant
    -0.69
     их
    -0.69
    Gauge
    -0.68
    lineHeight
    -0.68
    POSITIVE LOGITS
     lì
    0.84
     Lari
    0.81
     sní
    0.81
    memp
    0.80
    ďte
    0.79
     hollows
    0.77
     Torture
    0.77
    voyer
    0.75
     Antilles
    0.75
     })
    0.75
    Activations Density 0.024%

    No Known Activations