© 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. 22-GEMMASCOPE-RES-131K
    4. 11236
    Prev
    Next
    INDEX
    Explanations

    Average user, Please tell, Search This

    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
     you
    -1.37
     its
    -1.36
     where
    -1.30
     it
    -1.22
     also
    -1.19
     for
    -1.19
     helps
    -1.16
     usually
    -1.16
    foglio
    -1.13
     generally
    -1.13
    POSITIVE LOGITS
     admiten
    1.20
     (!__
    1.13
     Dingen
    1.11
    ebly
    1.03
    synonyms
    1.03
    ,
    0.99
    阯
    0.99
    מונות
    0.97
    rsquo
    0.96
    numeros
    0.96
    Activations Density 0.000%

    No Known Activations