© 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. 60069
    Prev
    Next
    INDEX
    Explanations

    cognizance, acquiesce, reminiscing, reconciling

    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
    ngdoc
    -0.82
    geology
    -0.73
    dB
    -0.73
    Guess
    -0.73
    oute
    -0.72
     Guess
    -0.71
    mainloop
    -0.70
    Baş
    -0.70
    joo
    -0.70
    guess
    -0.70
    POSITIVE LOGITS
    ance
    0.98
    ANCE
    0.88
    ances
    0.79
     Revival
    0.75
     mip
    0.71
     attendance
    0.69
     της
    0.69
    rance
    0.68
     flop
    0.68
     ancestral
    0.68
    Activations Density 0.053%

    No Known Activations