© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33630
    Prev
    Next
    INDEX
    Explanations

    questions followed by a number

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

    The neuron flags question marks (i.e. interrogative punctuation), marking the presence of questions.

    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
     this
    -1.47
     our
    -1.16
     After
    -1.16
     problems
    -1.15
    福田
    -1.13
     With
    -1.12
    勝負
    -1.11
     Even
    -1.09
    putable
    -1.09
    実感
    -1.08
    POSITIVE LOGITS
    ↵
    1.43
    のですか
    1.24
    artiges
    1.16
     vatten
    1.13
     maniere
    1.13
     refroid
    1.10
     plastiques
    1.09
     remplacer
    1.09
    際は
    1.05
    melden
    1.05
    Activations Density 0.058%

    No Known Activations