© 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. 34037
    Prev
    Next
    INDEX
    Explanations

    officials or entities acting

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

    The neuron fires on multi‐word proper names and organization or institution names (i.e. named entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ᴘ
    -1.30
    ♭
    -1.27
     }},
    -1.25
    $;
    -1.21
    ❓
    -1.20
    ;
    -1.20
     même
    -1.20
    か月
    -1.19
    ஸ்
    -1.18
    Bahkan
    -1.18
    POSITIVE LOGITS
     will
    2.25
     has
    2.13
     today
    1.80
     have
    1.77
     yesterday
    1.55
     Tuesday
    1.52
     Thursday
    1.40
    harmed
    1.36
     did
    1.34
     said
    1.34
    Activations Density 0.137%

    No Known Activations