© 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. 22-GEMMASCOPE-RES-131K
    7. 64864
    Prev
    Next
    INDEX
    Explanations

    Objective-C IBAction methods and C/C++ void functions

    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_22/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
     dentes
    -0.94
    lerinin
    -0.94
     Consejos
    -0.90
    蟥
    -0.88
     our
    -0.87
    犼
    -0.86
     JAXB
    -0.86
     sive
    -0.85
    necessary
    -0.85
    kinds
    -0.84
    POSITIVE LOGITS
    0.92
    You
    0.85
     you
    0.84
     даже
    0.83
    Although
    0.83
     vaksinasi
    0.83
    あなたが
    0.81
    It
    0.81
     $(
    0.80
     лишь
    0.79
    Activations Density 0.008%

    No Known Activations