© 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. 10-GEMMASCOPE-RES-131K
    7. 29146
    Prev
    Next
    INDEX
    Explanations

    limitation

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

    the word “only” 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_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
     misma
    -1.68
    </th>
    -1.49
     cump
    -1.45
     samme
    -1.41
     each
    -1.39
     pasas
    -1.39
     valida
    -1.38
     chaque
    -1.38
     frase
    -1.36
     hierdie
    -1.33
    POSITIVE LOGITS
    0
    1.74
     breiten
    1.73
     tiefen
    1.65
     weißen
    1.63
     obscured
    1.59
    真的好
    1.59
     Teilnahme
    1.59
    6
    1.57
     orgánica
    1.57
    かもしれませんが
    1.52
    Activations Density 0.021%

    No Known Activations