© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38246
    Prev
    Next
    INDEX
    Explanations

    meetings and mountain peaks

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

    The neuron activates on occurrences of the word “summit” (including split subtokens like “Sum” + “mit”), especially as part of event or title 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_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
    2
    -3.14
    5
    -2.58
    0
    -2.55
    訁
    -2.33
    9
    -2.30
     kterou
    -2.23
    8
    -2.20
    1
    -2.14
     wszystkich
    -2.13
    胳
    -2.06
    POSITIVE LOGITS
    戕
    3.09
    ୈ
    2.67
     barna
    2.67
    与此同时
    2.61
    ⦊
    2.59
    郇
    2.53
    釓
    2.50
    峩
    2.42
    琁
    2.42
     burbu
    2.41
    Activations Density 0.002%

    No Known Activations