© 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. 22-GEMMASCOPE-RES-131K
    7. 130690
    Prev
    Next
    INDEX
    Explanations

    sequence separators

    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
    
    -1.85
    pozdrawiam
    -1.66
     venturing
    -1.63
    enterOuterAlt
    -1.62
    ться
    -1.60
    𓄹
    -1.59
    Pozdrawiam
    -1.58
    Polecam
    -1.57
    Dziękuję
    -1.57
     continues
    -1.55
    POSITIVE LOGITS
     is
    1.55
    at
    1.52
    "
    1.49
    s
    1.48
    噼
    1.46
    “
    1.39
    O
    1.39
     ])
    1.38
     but
    1.37
     salvajes
    1.36
    Activations Density 0.012%

    No Known Activations