© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13086
    Prev
    Next
    INDEX
    Explanations

    achieve something by doing it

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

    The neuron activates on verbs meaning “to achieve or accomplish” (e.g. achieve, accomplish).

    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
    PASSWORD
    -1.50
     banheiro
    -1.48
    ་་
    -1.43
    >//
    -1.41
    〙
    -1.37
     爆
    -1.36
     núm
    -1.36
     mystérie
    -1.34
    ASYNC
    -1.34
     testator
    -1.34
    POSITIVE LOGITS
     by
    4.09
     with
    2.92
     on
    2.42
     through
    2.23
     via
    2.14
     from
    1.99
     like
    1.84
    by
    1.80
     without
    1.69
     путем
    1.55
    Activations Density 0.286%

    No Known Activations