© 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. 104692
    Prev
    Next
    INDEX
    Explanations

    problematic or excessive situations

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

    The neuron responds to words that denote threat or danger—especially terms like “menace,” “menacing,” and “rampant.”

    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
    ные
    -2.84
    酲
    -2.80
    玧
    -2.70
    ]
    -2.66
    ”;
    -2.64
    }
    -2.58
    ”(
    -2.52
    ”?
    -2.52
    姈
    -2.52
    ”:
    -2.50
    POSITIVE LOGITS
     The
    2.33
    </b>
    2.25
    VIATIONS
    2.22
    佧
    2.20
     😂
    1.98
     wirklich
    1.97
     élevés
    1.93
     freaking
    1.91
     sekarang
    1.90
     sommeil
    1.89
    Activations Density 0.001%

    No Known Activations