© 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. 10-GEMMASCOPE-RES-131K
    7. 59444
    Prev
    Next
    INDEX
    Explanations

    Milford, Avon, Mio, River, Police

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

    The neuron strongly activates on capitalized proper names—especially geographic place names.

    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
    B
    -2.61
    }
    -2.58
    er
    -2.58
    ;
    -2.52
    an
    -2.52
    .,
    -2.48
     prioriti
    -2.47
    逦
    -2.47
                    
    -2.45
    de
    -2.39
    POSITIVE LOGITS
    𓍊
    3.13
    ي
    3.02
    
    2.81
    Gruss
    2.69
    tentu
    2.67
    AdvEx
    2.59
    敺
    2.58
    〮
    2.55
    ㄚ
    2.55
     娃娃
    2.53
    Activations Density 0.004%

    No Known Activations