© 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-16K
    7. 4897
    Prev
    Next
    INDEX
    Explanations

    Merge Sort, GPT-4, Succession, King Charles III, Crash Bandicoot

    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_16k_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
     iccad
    0.41
     cốt
    0.40
    ی
    0.40
    赟
    0.39
     orchards
    0.38
     yǒu
    0.38
     observables
    0.38
     primarySwatch
    0.37
     ایسا
    0.36
    琹
    0.36
    POSITIVE LOGITS
    ag
    0.47
    iven
    0.45
    uk
    0.44
    ular
    0.43
    ral
    0.43
     frightened
    0.43
    ake
    0.42
    xious
    0.42
    ap
    0.42
    ht
    0.41
    Activations Density 0.201%

    No Known Activations