© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1569
    Prev
    Next
    INDEX
    Explanations

    Douglas County government

    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
    Passive
    -0.89
    cordia
    -0.86
     passive
    -0.82
    компа
    -0.80
    วิธี
    -0.78
     Sloane
    -0.77
    avir
    -0.77
     černé
    -0.74
    izarro
    -0.74
    passive
    -0.73
    POSITIVE LOGITS
     lass
    0.72
     stam
    0.71
    leer
    0.70
    .(*
    0.68
     boş
    0.66
    Composable
    0.66
    *(
    0.65
     whereof
    0.64
    >):
    0.64
     tapp
    0.64
    Activations Density 0.029%

    No Known Activations