© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73010
    Prev
    Next
    INDEX
    Explanations

    help to improve or manage

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

    The neuron fires on present-tense action verbs that convey helping, securing, facilitating, or otherwise enabling something.

    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
     estancias
    -1.46
    
    -1.42
    炻
    -1.42
    currPos
    -1.41
     haci
    -1.38
    ActionTypes
    -1.35
     in
    -1.32
    ⢎
    -1.32
    postIndex
    -1.32
     посмотреть
    -1.30
    POSITIVE LOGITS
    to
    1.57
    </b>
    1.53
    完全に
    1.50
    </i>
    1.45
    ti
    1.42
    www
    1.33
    擄
    1.28
    and
    1.25
    got
    1.25
     zahlreichen
    1.22
    Activations Density 0.086%

    No Known Activations