© 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. 10-GEMMASCOPE-RES-131K
    7. 20462
    Prev
    Next
    INDEX
    Explanations

    report incidents/issues

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

    The neuron activates on imperative calls to “report” (i.e., occurrences of the verb “report” in instruction contexts).

    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
    ↵↵
    -2.52
    "
    -1.88
    ">
    -1.69
     их
    -1.63
    *
    -1.60
    ]
    -1.55
    糞
    -1.52
    Ḥ
    -1.52
     "
    -1.49
     idée
    -1.47
    POSITIVE LOGITS
     to
    2.31
     being
    1.96
     verwijzen
    1.91
    棡
    1.88
     Pristup
    1.77
     bellissimo
    1.77
     gatto
    1.77
     settimane
    1.76
     at
    1.75
    ᾥ
    1.74
    Activations Density 0.027%

    No Known Activations