© 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. 39634
    Prev
    Next
    INDEX
    Explanations

    general and category

    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
    癭
    -2.92
     présentent
    -2.91
     donnent
    -2.78
     relentless
    -2.75
     "
    -2.64
    瓛
    -2.61
     immense
    -2.58
     nonchal
    -2.56
    珵
    -2.53
    皛
    -2.52
    POSITIVE LOGITS
    1
    3.98
    7
    3.67
    6
    3.58
    4
    3.47
    8
    3.41
    5
    3.13
    Even
    3.02
    2
    2.98
    3
    2.97
    9
    2.89
    Activations Density 0.062%

    No Known Activations