© 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. 10735
    Prev
    Next
    INDEX
    Explanations

    tracking information

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

    The neuron strongly activates on verbs denoting monitoring or management actions—especially “track” (and to a lesser extent “manage”).

    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
    "
    -2.42
    }
    -2.28
    *
    -1.94
    [
    -1.93
    -
    -1.90
    (
    -1.89
            
    -1.86
    >
    -1.80
    )
    -1.80
    ]
    -1.80
    POSITIVE LOGITS
     expédi
    1.70
     timmar
    1.69
    ſus
    1.63
    珖
    1.59
    豋
    1.59
     aktivitet
    1.55
     ASPECTS
    1.49
    CurtirCurtir
    1.46
    Usos
    1.46
     variar
    1.46
    Activations Density 0.038%

    No Known Activations