© 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. 20594
    Prev
    Next
    INDEX
    Explanations

    phone numbers or years

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

    currency and temperature units

    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
     escena
    0.46
    Ⴚ
    0.41
     actitud
    0.39
    спонд
    0.39
     నేపథ్యంలో
    0.38
     అధిక
    0.38
     sepol
    0.38
     sacerd
    0.37
    Scheme
    0.37
    ներ
    0.37
    POSITIVE LOGITS
    成
    0.38
    .''
    0.36
    iels
    0.36
    ható
    0.36
    ielen
    0.35
    성
    0.34
    痳
    0.34
    ussy
    0.34
     吃
    0.34
    美
    0.34
    Activations Density 0.075%

    No Known Activations