© 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. 46131
    Prev
    Next
    INDEX
    Explanations

    consider, need, create, serving

    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
    귀
    0.48
     Jefe
    0.48
    рами
    0.46
     Itália
    0.45
     Parmi
    0.43
    ريق
    0.43
    λοι
    0.43
     Inglaterra
    0.42
    кус
    0.42
    창
    0.42
    POSITIVE LOGITS
     poems
    0.55
    ule
    0.52
    ando
    0.52
     lesions
    0.52
     arteries
    0.52
     through
    0.50
     sensitive
    0.50
     anger
    0.50
     songs
    0.50
     answering
    0.49
    Activations Density 0.004%

    No Known Activations