© 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. 70826
    Prev
    Next
    INDEX
    Explanations

    fear, rigors, meaning, bonus, lights

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

    specific technical concepts

    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
     المرأة
    0.52
    ش
    0.46
    잦
    0.45
    ADA
    0.43
    с
    0.43
    ш
    0.43
     waffles
    0.43
    糁
    0.42
     croissant
    0.42
     haircut
    0.41
    POSITIVE LOGITS
     Dionys
    0.45
     inmedi
    0.43
    Ꭾ
    0.42
    當時
    0.40
     Adem
    0.40
     innumerable
    0.39
     plummet
    0.38
    hibit
    0.38
    mittel
    0.38
    byter
    0.38
    Activations Density 0.001%

    No Known Activations