© 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-262K
    7. 203665
    Prev
    Next
    INDEX
    Explanations

    eventually correcting value

    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_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
    strom
    0.45
    Sept
    0.44
    K
    0.43
    zna
    0.42
    ysen
    0.42
    plant
    0.41
    U
    0.41
    Table
    0.41
     new
    0.40
    tube
    0.40
    POSITIVE LOGITS
     каждая
    0.55
    нэ
    0.54
    ູ້
    0.52
    㧍
    0.48
    是最
    0.48
    ஷ
    0.48
     इनवर्स
    0.48
     controladores
    0.47
    会计
    0.47
    我们
    0.47
    Activations Density 0.004%

    No Known Activations