© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102532
    Prev
    Next
    INDEX
    Explanations

    resource manager

    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
     Shao
    -0.76
    hort
    -0.72
     reef
    -0.70
     Botany
    -0.69
     resent
    -0.69
    JH
    -0.69
    ➾
    -0.68
    악
    -0.68
    ⅹ
    -0.67
    valence
    -0.66
    POSITIVE LOGITS
    Group
    0.97
     Group
    0.86
    inferior
    0.78
    GroupName
    0.76
     GROUP
    0.75
     Groups
    0.73
    gruppen
    0.73
     Inferior
    0.72
    Within
    0.71
     PROV
    0.71
    Activations Density 0.042%

    No Known Activations