© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56957
    Prev
    Next
    INDEX
    Explanations

    polynomials and algorithms

    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
     lois
    -0.93
     bandera
    -0.87
    花园
    -0.86
    ☽
    -0.84
    arate
    -0.83
     LETTER
    -0.82
    йтинг
    -0.81
     minera
    -0.81
    究極
    -0.81
     Schwab
    -0.79
    POSITIVE LOGITS
     Syndrome
    0.90
     syndrome
    0.83
     gadget
    0.80
     incurred
    0.79
     amor
    0.78
     Claim
    0.78
     laminar
    0.77
    昱
    0.77
     poly
    0.76
    CKS
    0.76
    Activations Density 0.051%

    No Known Activations