© 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. 10-GEMMASCOPE-RES-131K
    7. 86356
    Prev
    Next
    INDEX
    Explanations

    Molly followed by names or thunderstorms

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

    The neuron is looking for mentions of “thunderstorm” (including its plural and compound forms).

    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
     You
    -2.77
     vostra
    -2.64
     These
    -2.63
    ╿
    -2.53
    冏
    -2.45
    蠖
    -2.45
     fratelli
    -2.42
    zzlement
    -2.38
    einem
    -2.31
    ください
    -2.30
    POSITIVE LOGITS
    瑧
    2.94
    ↵↵
    2.78
    }
    2.72
    v
    2.66
    「
    2.59
    <i>
    2.58
     одна
    2.47
    5
    2.45
     –
    2.44
    2
    2.41
    Activations Density 0.007%

    No Known Activations