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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7215
    Prev
    Next
    INDEX
    Explanations

    personal life details

    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
    kese
    -1.13
    PictureBox
    -1.02
    のある
    -0.98
    ука
    -0.97
     palavras
    -0.96
     pegawai
    -0.94
     croissants
    -0.92
     あり
    -0.92
    för
    -0.92
     nossas
    -0.91
    POSITIVE LOGITS
    ty
    1.20
     preference
    1.14
    izable
    1.14
    personal
    1.13
     personal
    1.13
     никогда
    1.13
     hygiene
    1.12
    bestand
    1.10
    にほんブログ村
    1.06
    Personal
    1.05
    Activations Density 0.021%

    No Known Activations