© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65956
    Prev
    Next
    INDEX
    Explanations

    letter where

    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_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
     TÉCNICA
    -1.55
    Recent
    -1.53
    excellents
    -1.48
     گیاه
    -1.44
     desiderio
    -1.32
     τὴν
    -1.30
     Gottesdienst
    -1.27
    昨日の
    -1.27
     hábit
    -1.27
     TÉCN
    -1.26
    POSITIVE LOGITS
    ּוֹ
    1.80
    וּ
    1.69
    ֶּ
    1.55
    וּ
    1.48
    醣
    1.46
    ְּ
    1.39
    seamnă
    1.37
    ַּ
    1.37
    ִּ
    1.36
    ícia
    1.31
    Activations Density 0.040%

    No Known Activations