© 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. 11715
    Prev
    Next
    INDEX
    Explanations

    misspellings and proper nouns

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

    The neuron flags discussion of “typo”-type tokens—i.e. words referring to typographical errors.

    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
    बाइल
    -2.48
    vantaged
    -2.47
     kompeti
    -2.36
    뜩
    -2.23
    
    -2.20
    This
    -2.17
    these
    -2.16
    cinations
    -2.16
    );
    -2.11
    平静
    -2.11
    POSITIVE LOGITS
    倥
    2.47
    d
    2.42
    l
    2.41
     legitimately
    2.30
     you
    2.30
     tetapi
    2.25
     einzigen
    2.25
     принцип
    2.19
     we
    2.14
    塍
    2.14
    Activations Density 0.008%

    No Known Activations