© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103725
    Prev
    Next
    INDEX
    Explanations

    shore and coast line

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

    The neuron primarily detects occurrences of the substring “shore” (e.g. in words or names containing “shore”).

    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
    dend
    -0.81
    FLOOR
    -0.81
    USERNAME
    -0.81
    ビール
    -0.77
    richText
    -0.76
    combination
    -0.75
    flor
    -0.75
    Doors
    -0.75
     kuat
    -0.74
    riott
    -0.74
    POSITIVE LOGITS
    line
    1.19
     línea
    0.97
    LINE
    0.96
     leave
    0.95
     line
    0.94
    hore
    0.91
     Leave
    0.89
    side
    0.88
    躇
    0.83
    üns
    0.77
    Activations Density 0.006%

    No Known Activations