© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 45079
    Prev
    Next
    INDEX
    Explanations

    URLs and git commits

    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
     व
    0.41
     मुख्यतः
    0.41
    udit
    0.40
    amad
    0.40
    的
    0.40
    熙
    0.40
    IU
    0.39
    عود
    0.39
    ե
    0.39
    ད་
    0.39
    POSITIVE LOGITS
     bajos
    0.49
     personaggio
    0.49
     této
    0.48
     singolo
    0.47
     obiettivo
    0.46
     doel
    0.46
     tejto
    0.45
     этом
    0.45
     düşük
    0.45
     LOWER
    0.44
    Activations Density 0.008%

    No Known Activations