© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43300
    Prev
    Next
    INDEX
    Explanations

    except for

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the phrase “except for,” flagging exception clauses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵↵
    -2.14
    .
    -1.67
     
    -1.66
    c
    -1.60
     où
    -1.57
    p
    -1.55
    an
    -1.55
     Concerning
    -1.51
    as
    -1.50
     Situated
    -1.48
    POSITIVE LOGITS
     those
    2.31
    ("
    2.30
     récente
    2.05
     a
    2.05
     but
    1.90
    、“
    1.84
     höl
    1.83
     costuras
    1.82
    følgelig
    1.80
    !’
    1.79
    Activations Density 0.003%

    No Known Activations