© 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. 84399
    Prev
    Next
    INDEX
    Explanations

    forest place names

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

    The neuron specifically activates on occurrences of the word “Forest” (often as part of proper 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
    甞
    -3.45
    漚
    -3.30
    栳
    -2.89
    儅
    -2.88
    section
    -2.86
    鼉
    -2.80
    鲧
    -2.78
    跸
    -2.75
     ſch
    -2.70
    ed
    -2.63
    POSITIVE LOGITS
     для
    3.53
     untuk
    3.22
    It
    3.06
    to
    3.05
    ]
    2.89
    ),
    2.80
     чтобы
    2.69
    for
    2.63
     всех
    2.59
    -
    2.58
    Activations Density 0.005%

    No Known Activations