© 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. 11992
    Prev
    Next
    INDEX
    Explanations

    asking how to

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

    The neuron flags interrogative “how” constructions (especially “how to”/“how can I” question phrases).

    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
     nevera
    -1.34
     akrab
    -1.23
     botines
    -1.23
     vélos
    -1.17
    لباس
    -1.16
    shows
    -1.15
    might
    -1.14
    Bakgrunns
    -1.14
    unfortunately
    -1.14
    cketed
    -1.13
    POSITIVE LOGITS
     can
    2.22
     could
    1.76
     are
    1.75
     did
    1.74
     to
    1.59
     will
    1.54
     should
    1.54
     would
    1.45
     does
    1.44
     was
    1.43
    Activations Density 0.084%

    No Known Activations