© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107841
    Prev
    Next
    INDEX
    Explanations

    World Bank, Tower Hamlets, Application

    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
     achet
    -0.82
    ⑶
    -0.78
     BELIEVE
    -0.77
    ᑕ
    -0.77
    лях
    -0.77
     预
    -0.75
     安卓
    -0.75
     overla
    -0.74
    Nie
    -0.74
     Queer
    -0.73
    POSITIVE LOGITS
     gave
    0.77
    FIB
    0.76
     drogas
    0.75
    octave
    0.74
     Desmond
    0.73
     had
    0.73
     zdrowia
    0.73
    وض
    0.73
     may
    0.73
     connected
    0.72
    Activations Density 0.001%

    No Known Activations