© 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. 84256
    Prev
    Next
    INDEX
    Explanations

    scan results

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

    This neuron fires strongly on short letter‐sequence fragments (3–4 letters) that are parts of longer tokens rather than on complete words.

    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
     first
    -1.15
    ־ה
    -1.14
     chose
    -1.14
     until
    -1.13
     out
    -1.13
    וּ
    -1.13
     several
    -1.11
     various
    -1.09
     for
    -1.09
     amidst
    -1.06
    POSITIVE LOGITS
     {$\
    1.35
     ß
    1.35
     {?}
    1.30
     .........
    1.27
     kulinar
    1.22
     majestic
    1.20
     $\{$
    1.20
     ........
    1.20
     shimmering
    1.19
     câbles
    1.18
    Activations Density 0.001%

    No Known Activations