© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63171
    Prev
    Next
    INDEX
    Explanations

    except but minus

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

    The neuron fires on technical or domain-specific nouns that serve as labels or category names (e.g. “conference,” “unit,” “technique,” “dictionary,” “Oscars”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    uſe
    -0.99
    compared
    -0.98
     compared
    -0.96
    っていると
    -0.95
     像
    -0.95
    itab
    -0.95
     keinem
    -0.93
    像
    -0.93
    jarige
    -0.93
     beyond
    -0.92
    POSITIVE LOGITS
     except
    3.84
     but
    3.45
     minus
    3.02
     only
    2.97
    只不过
    2.95
    except
    2.89
    minus
    2.69
     только
    2.53
     Except
    2.52
    只是
    2.48
    Activations Density 0.129%

    No Known Activations