© 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. 129224
    Prev
    Next
    INDEX
    Explanations

    code related to increment or enumerate

    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
     sereia
    -0.99
     دارم
    -0.88
     schönes
    -0.88
    zeile
    -0.88
     feminina
    -0.87
    Istwa
    -0.87
     some
    -0.85
     œufs
    -0.84
    contentValues
    -0.83
     partielle
    -0.82
    POSITIVE LOGITS
    👈
    0.88
    middelen
    0.83
    brooke
    0.83
    ीन
    0.82
    wirk
    0.79
    Sint
    0.78
    prin
    0.78
    子的
    0.77
    ximation
    0.77
     loop
    0.76
    Activations Density 0.010%

    No Known Activations