© 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. 128224
    Prev
    Next
    INDEX
    Explanations

    This neuron detects content‐language declarations—that is, two-letter language codes (like “cs”) in metadata headers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical document starts

    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
     those
    -1.05
     work
    -0.94
    envol
    -0.89
    してくれた
    -0.86
     up
    -0.85
    ednesday
    -0.84
     sparked
    -0.83
     chose
    -0.82
     desperately
    -0.81
     job
    -0.81
    POSITIVE LOGITS
    result
    1.01
     "="
    1.00
    ggable
    0.94
     crores
    0.93
    no
    0.93
    except
    0.93
     nabíz
    0.93
    should
    0.93
    ظهر
    0.93
    UT
    0.92
    Activations Density 0.000%

    No Known Activations