© 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. 34-GEMMASCOPE-RES-131K
    4. 102384
    Prev
    Next
    INDEX
    Explanations

    Long layover

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

    The neuron is triggered by long runs of space characters (i.e. extended whitespace or indentation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     for
    -1.53
     in
    -1.52
     from
    -1.50
     or
    -1.47
     on
    -1.38
     by
    -1.38
     with
    -1.36
     as
    -1.35
     it
    -1.33
     if
    -1.30
    POSITIVE LOGITS
    </em>
    1.51
    </blockquote>
    1.35
    </td>
    1.20
     大きい
    1.09
     réduire
    1.07
     établir
    1.06
    </i>
    1.03
     périodes
    1.03
     crescita
    1.02
    ఱ
    1.02
    Activations Density 0.000%

    No Known Activations