© 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. 129075
    Prev
    Next
    INDEX
    Explanations

    The neuron flags words that indicate navigating or traversing through a sequence or list (e.g. last, next, over, other).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    count of items

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    河南
    -1.25
    Begriffsklä
    -1.20
    全球
    -1.18
    我们
    -1.18
    大家
    -1.18
    谙
    -1.13
    ritsar
    -1.09
    Vezi
    -1.09
    ֎
    -1.08
    新型コロナ
    -1.07
    POSITIVE LOGITS
     items
    1.55
     pieces
    1.37
     elements
    1.30
     things
    1.21
     member
    1.19
     students
    1.19
     something
    1.19
     recientes
    1.18
     materials
    1.15
    Примеча
    1.15
    Activations Density 0.194%

    No Known Activations