© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16116
    Prev
    Next
    INDEX
    Explanations

    math, errors, percentage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    念
    0.60
    Thought
    0.56
    GL
    0.55
    thought
    0.55
    Expect
    0.55
    Prayer
    0.55
    獅
    0.54
    펩
    0.54
    WE
    0.54
    mom
    0.52
    POSITIVE LOGITS
     errore
    0.81
     errors
    0.79
     errori
    0.73
     error
    0.72
     substring
    0.70
     erreur
    0.69
    エラー
    0.69
     flowchart
    0.64
     svært
    0.64
     jpeg
    0.64
    Activations Density 0.001%

    No Known Activations