© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45250
    Prev
    Next
    INDEX
    Explanations

    scale and magnitude

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

    The neuron responds to mentions of “scale” or “large-scale” contexts describing magnitude or size.

    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
    轵
    -1.53
    ☺☺
    -1.47
     când
    -1.46
     壁纸
    -1.45
    wendi
    -1.44
     nuoc
    -1.41
    があり
    -1.39
    esterday
    -1.38
     ſch
    -1.36
    </td>
    -1.35
    POSITIVE LOGITS
    lemented
    1.60
    "]
    1.49
    弱点
    1.47
     другое
    1.46
     уже
    1.41
    </h4>
    1.41
     remainder
    1.41
     esencia
    1.38
     стоимости
    1.38
    lusconi
    1.35
    Activations Density 0.025%

    No Known Activations