© 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. 108720
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License versions

    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
     suéter
    -0.92
     grocery
    -0.84
     voltaje
    -0.83
     kasih
    -0.82
    avocat
    -0.81
    ोड
    -0.80
     débuts
    -0.78
    says
    -0.78
     acuario
    -0.77
     logistique
    -0.76
    POSITIVE LOGITS
     marc
    0.81
    keyframes
    0.77
    kou
    0.75
    久
    0.74
     Dict
    0.74
     почув
    0.74
     Herd
    0.73
    ബ
    0.72
     Analyst
    0.72
    "]));
    0.72
    Activations Density 0.002%

    No Known Activations