© 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. 953
    Prev
    Next
    INDEX
    Explanations

    text tables with |

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     is
    -1.97
     ‘
    -1.73
    </h4>
    -1.52
     or
    -1.49
    ”
    -1.48
     ”
    -1.45
     a
    -1.45
     as
    -1.44
    !’
    -1.43
     shouldn
    -1.41
    POSITIVE LOGITS
    য়া
    1.49
    今日は
    1.48
    𝐏
    1.48
     valde
    1.45
    sierung
    1.38
    鹟
    1.37
     poitrine
    1.37
     ответственность
    1.34
    𝐁
    1.34
    espół
    1.33
    Activations Density 0.005%

    No Known Activations