© 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. 40-GEMMASCOPE-2-RES-262K
    7. 167644
    Prev
    Next
    INDEX
    Explanations

    timing or metrics

    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_40_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
     Trường
    0.46
     operaciones
    0.43
    휋
    0.42
     rechten
    0.41
    newTask
    0.41
    icky
    0.41
     operações
    0.40
     thấm
    0.40
     operazioni
    0.40
     明
    0.39
    POSITIVE LOGITS
    スル
    0.40
    疽
    0.39
     recreational
    0.38
     diagnosis
    0.38
    診
    0.37
     auxiliary
    0.36
    ったり
    0.36
     fancy
    0.36
     Conception
    0.35
     casual
    0.35
    Activations Density 0.003%

    No Known Activations