© 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. 22-GEMMASCOPE-RES-131K
    7. 27402
    Prev
    Next
    INDEX
    Explanations

    .net or NetVista

    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_22/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
    ellement
    -1.05
    Ň
    -1.00
    izzera
    -0.98
     tono
    -0.94
     we
    -0.92
     monstre
    -0.91
    년
    -0.89
     polie
    -0.89
     pè
    -0.89
    宍
    -0.87
    POSITIVE LOGITS
    ffè
    0.92
     इसका
    0.90
    提出
    0.86
    atakan
    0.85
     ungef
    0.85
    第一
    0.84
    様々な
    0.83
    itse
    0.82
     erwähnten
    0.82
    0.81
    Activations Density 0.005%

    No Known Activations