© 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. 34-GEMMASCOPE-RES-131K
    7. 90435
    Prev
    Next
    INDEX
    Explanations

    :

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

    The neuron fires on meaningful content words—nouns, verbs, and adjectives—while ignoring common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ykjav
    -1.53
     aDecoder
    -1.49
    要不然
    -1.34
    紝
    -1.27
    istible
    -1.26
     and
    -1.22
    你不
    -1.19
    verns
    -1.18
    幸好
    -1.17
    先前
    -1.16
    POSITIVE LOGITS
    :
    5.59
    :
    3.59
    ():
    3.16
    ):
    2.86
    :</
    2.64
     []:
    2.63
    ():
    2.56
    ):
    2.53
    ：……
    2.52
    ]:
    2.45
    Activations Density 0.899%

    No Known Activations