© 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. 92837
    Prev
    Next
    INDEX
    Explanations

    Led Zeppelin, surgical site, the first

    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
     it
    -0.86
     ਸ
    -0.85
     over
    -0.83
    avaa
    -0.79
    abá
    -0.79
     NOW
    -0.77
    łem
    -0.77
     ס
    -0.76
     Ο
    -0.76
    Rgds
    -0.75
    POSITIVE LOGITS
     IJ
    0.98
     monthly
    0.94
     Ambulance
    0.94
     '|
    0.88
     carcinoma
    0.86
    ITUTE
    0.85
     cheetah
    0.84
     *-
    0.84
     arduino
    0.83
    𝑞
    0.83
    Activations Density 0.003%

    No Known Activations