© 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. 117041
    Prev
    Next
    INDEX
    Explanations

    unit test / normal vector

    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
    ení
    -0.79
    ım
    -0.75
    Princip
    -0.73
    })$}
    -0.71
    弔
    -0.70
    洋
    -0.69
     noticia
    -0.68
     dirigido
    -0.68
    ẵn
    -0.68
    etap
    -0.67
    POSITIVE LOGITS
     UNIT
    1.02
     circle
    0.96
     unit
    0.88
    unit
    0.84
    UNIT
    0.82
    Unit
    0.81
     Unit
    0.77
     conversions
    0.77
    cted
    0.74
    lators
    0.74
    Activations Density 0.021%

    No Known Activations