© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 94275
    Prev
    Next
    INDEX
    Explanations

    factors and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    0.47
     Marijuana
    0.46
     Marie
    0.43
    Marie
    0.43
    在
    0.42
     Pur
    0.42
     আসন্ন
    0.40
    期
    0.40
    一
    0.40
    家庭
    0.39
    POSITIVE LOGITS
     uridine
    0.65
     dimensione
    0.60
     tamanho
    0.57
     buty
    0.52
     embryo
    0.52
     dimensionality
    0.52
     formato
    0.51
     fluxo
    0.51
     taxas
    0.51
     waveforms
    0.51
    Activations Density 0.018%

    No Known Activations