© 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. 22-GEMMASCOPE-RES-131K
    4. 73717
    Prev
    Next
    INDEX
    Explanations

    self storage units

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

    The neuron fires on isolated numeric tokens (standalone numbers) in the text.

    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
     can
    -1.06
     також
    -1.01
    อีก
    -0.94
     Only
    -0.92
    <eos>
    -0.91
     wiederum
    -0.91
     which
    -0.88
    又
    -0.88
     also
    -0.87
    —
    -0.87
    POSITIVE LOGITS
     zunächst
    1.09
     â
    1.05
     pertama
    1.02
    namientos
    1.01
    cheme
    0.99
     cubiertos
    0.97
     geweldig
    0.97
    lettes
    0.96
     ï
    0.96
    coring
    0.96
    Activations Density 0.016%

    No Known Activations