© 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. 22-GEMMASCOPE-RES-131K
    7. 75309
    Prev
    Next
    INDEX
    Explanations

    admission fees and free entry

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

    The main thing this neuron does is find mentions of admission pricing or “free admission” notices.

    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
     that
    -1.44
     
    -1.16
     when
    -1.16
     (
    -1.09
     what
    -1.09
     fehler
    -1.09
    が無い
    -1.05
     we
    -1.04
     new
    -1.02
     berço
    -1.01
    POSITIVE LOGITS
    ENING
    1.18
    ﻻ
    1.14
     accepte
    1.13
     free
    1.12
     enceinte
    1.09
    äť
    1.09
     admission
    1.09
     буде
    1.08
    Jahre
    1.08
     participants
    1.07
    Activations Density 0.013%

    No Known Activations