© 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. 37980
    Prev
    Next
    INDEX
    Explanations

    released after being held

    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
     Eingang
    -0.70
     bpy
    -0.70
     lukisan
    -0.70
    ennia
    -0.68
    ല്‍
    -0.67
    точный
    -0.66
    рем
    -0.66
    removeAll
    -0.66
     ПОД
    -0.64
    ieni
    -0.63
    POSITIVE LOGITS
     release
    6.81
     released
    6.06
    release
    5.81
     releases
    5.78
     Release
    5.72
    Release
    5.63
     releasing
    5.41
     RELEASE
    4.94
     Released
    4.78
    released
    4.63
    Activations Density 0.097%

    No Known Activations