© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47453
    Prev
    Next
    INDEX
    Explanations

    follow-only syndicate

    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
    textit
    -0.81
    ftance
    -0.78
     Aurang
    -0.75
    Die
    -0.74
     eccl
    -0.73
    睜
    -0.73
    ńcz
    -0.72
    Crown
    -0.71
    die
    -0.71
    aggia
    -0.69
    POSITIVE LOGITS
     catastrophe
    1.27
     ILS
    1.01
     ced
    1.01
     reins
    1.00
     treaty
    0.98
     Willis
    0.90
     capacity
    0.90
     Bermuda
    0.88
     hurricane
    0.87
     trapped
    0.85
    Activations Density 0.007%

    No Known Activations