© 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. 34-GEMMASCOPE-RES-131K
    7. 118058
    Prev
    Next
    INDEX
    Explanations

    this is / these are

    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_34/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
     volgt
    -1.53
    lorn
    -1.48
    kozások
    -1.43
     neemt
    -1.38
     hoort
    -1.37
    anmar
    -1.36
    €”
    -1.34
    ślę
    -1.33
    なんですよ
    -1.33
    erunner
    -1.30
    POSITIVE LOGITS
     is
    6.00
     was
    3.33
     are
    2.69
     είναι
    2.61
     isn
    2.56
    是
    2.27
     wasn
    2.27
     might
    2.06
     could
    2.00
     является
    1.98
    Activations Density 0.089%

    No Known Activations