© 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. 90850
    Prev
    Next
    INDEX
    Explanations

    what i'm looking for

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

    The neuron fires on occurrences of the phrase “looking for” (and close variants like “what you’re looking for”), i.e. expressions of search intent.

    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
    */
    
    -1.35
     и
    -1.34
     :"
    -1.34
    ?»
    -1.30
    uation
    -1.30
    toward
    -1.30
    »:
    -1.27
    anced
    -1.27
    thodoxy
    -1.27
     esfuer
    -1.24
    POSITIVE LOGITS
     when
    1.58
     with
    1.52
     infine
    1.27
     restricting
    1.23
     tabaco
    1.21
     interruptor
    1.20
    поді
    1.20
     valuable
    1.19
     containing
    1.18
     stating
    1.18
    Activations Density 0.083%

    No Known Activations