© 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. 22-GEMMASCOPE-RES-131K
    7. 84420
    Prev
    Next
    INDEX
    Explanations

    variable names or dictionary keys

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

    This neuron responds to the “.” token used in code, e.g. as the attribute/method‐access operator in Python (pandas) expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <bos>
    -1.28
    见状
    -1.17
     personnalité
    -1.16
     Offisielt
    -1.16
    hills
    -1.13
     그의
    -1.12
     juventud
    -1.11
     bailarina
    -1.09
     poemas
    -1.08
     réputation
    -1.08
    POSITIVE LOGITS
    ところに
    1.25
    えっ
    1.22
    を変更
    1.16
     lesquelles
    1.08
    MODIFIED
    1.07
     their
    1.05
     each
    1.03
    のだろう
    1.02
    <th>
    1.00
     chacune
    0.99
    Activations Density 0.012%

    No Known Activations