© 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. 86364
    Prev
    Next
    INDEX
    Explanations

    launching new things

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

    The neuron specifically detects occurrences of the “launch” root in words (e.g. launch, launched, launching).

    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
    -1.87
     gripping
    -1.80
    joyed
    -1.69
     ול
    -1.68
     REALLY
    -1.66
     WHILE
    -1.66
     そ
    -1.66
     ieri
    -1.65
     gewährle
    -1.64
     VERY
    -1.63
    POSITIVE LOGITS
    gencias
    1.88
    鞮
    1.73
    鲽
    1.69
     –
    1.67
    TacToe
    1.63
    tedrale
    1.62
     tanque
    1.61
    reté
    1.61
     дал
    1.61
    }$.
    1.60
    Activations Density 0.019%

    No Known Activations