© 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. 102774
    Prev
    Next
    INDEX
    Explanations

    actualIZATION, actualIZING, actualUPDATE

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

    The neuron activates on occurrences of the root “actual” (and its morphological variants like actualize/actualization, actualizar, atual, etc.).

    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
    }$
    -2.70
    翆
    -2.69
     -
    -2.44
     algunos
    -2.38
     "
    -2.28
     focussing
    -2.19
     aqueles
    -2.17
    </th>
    -2.17
    ...."
    -2.16
     inim
    -2.13
    POSITIVE LOGITS
    ?”
    3.13
    ↵
    2.42
    ～。
    2.22
    各样的
    2.20
    si
    2.11
    缐
    2.09
    W
    2.06
    ～♪
    2.02
    $
    2.02
    down
    2.00
    Activations Density 0.006%

    No Known Activations