© 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. 13741
    Prev
    Next
    INDEX
    Explanations

    purpose or reason

    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
     república
    -1.12
    適合
    -0.93
     docteur
    -0.92
     =-\
    -0.85
    ionado
    -0.84
    ону
    -0.84
    енча
    -0.84
    žem
    -0.84
     menghindari
    -0.84
     guitarra
    -0.84
    POSITIVE LOGITS
     into
    1.20
     from
    1.05
     someone
    1.05
    Someone
    0.98
    sters
    0.94
     gram
    0.91
    thers
    0.90
     tratan
    0.90
     glisser
    0.90
    someone
    0.90
    Activations Density 0.103%

    No Known Activations