© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133945
    Prev
    Next
    INDEX
    Explanations

    gas height, before the, so use

    np_acts-logits-general · gemini-2.5-flash-lite

    foreign characters and English phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     i
    0.52
     fes
    0.50
     mehreren
    0.47
     marshes
    0.47
     a
    0.46
     ii
    0.46
     poche
    0.45
     ases
    0.45
     aantal
    0.44
     moll
    0.44
    POSITIVE LOGITS
     달리
    0.45
     ధర
    0.44
    ponsorship
    0.44
     못
    0.42
    custId
    0.42
    šķ
    0.42
    Email
    0.41
    gunakan
    0.41
    barang
    0.41
     చెప్పు
    0.41
    Activations Density 0.000%

    No Known Activations