© 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. 25
    Prev
    Next
    INDEX
    Explanations

    will find

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

    The neuron detects second-person future-tense phrases (e.g. “you will” or “you’ll”).

    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
     what
    -1.41
     you
    -1.28
    <_>
    -1.23
     its
    -1.22
     kecil
    -1.18
     Charles
    -1.15
     JUST
    -1.15
     take
    -1.13
     September
    -1.13
     Taking
    -1.13
    POSITIVE LOGITS
     need
    1.66
    ビックリ
    1.32
     finds
    1.24
    find
    1.21
    なども
    1.21
    色んな
    1.20
    も含
    1.19
    ,
    1.18
     moeten
    1.18
     encontrar
    1.18
    Activations Density 0.022%

    No Known Activations