© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 32191
    Prev
    Next
    INDEX
    Explanations

    evidence, originals, documents

    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
    方
    0.44
    子
    0.44
     competency
    0.41
     screening
    0.41
    })
    0.39
    IfNeeded
    0.39
    即可
    0.39
    `.
    0.39
    .`
    0.37
     模型
    0.37
    POSITIVE LOGITS
     మాత్రం
    0.47
     हालत
    0.46
    setNome
    0.46
     todavía
    0.45
     definitivo
    0.44
    ısıyla
    0.44
    တွေကို
    0.44
    électricité
    0.44
    食べて
    0.43
    実際に
    0.42
    Activations Density 0.012%

    No Known Activations