© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50039
    Prev
    Next
    INDEX
    Explanations

    socks, tends, sparse representation, establishment sentiment

    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_65k_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
     rearranging
    0.46
     নামাজের
    0.46
     viviendas
    0.45
    that
    0.43
    allowing
    0.42
     that
    0.42
     mohou
    0.42
    鿷
    0.41
    ängen
    0.41
     breakage
    0.41
    POSITIVE LOGITS
     Accred
    0.44
     Labour
    0.42
     Champions
    0.41
    ondale
    0.41
     tại
    0.40
    𝒓
    0.40
     Esq
    0.40
     accredited
    0.39
     Accreditation
    0.39
     Retail
    0.39
    Activations Density 0.002%

    No Known Activations