© 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. 46137
    Prev
    Next
    INDEX
    Explanations

    supported by

    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
     ಮೊ
    0.40
     dugo
    0.39
    লীর
    0.39
     ईयर
    0.38
     sukham
    0.38
    腆
    0.38
     liquido
    0.38
    ನಿ
    0.37
    あたり
    0.37
    虑
    0.37
    POSITIVE LOGITS
     casc
    0.48
     cascade
    0.47
     cascading
    0.46
    to
    0.45
     maximising
    0.44
    Cascade
    0.42
    Nearest
    0.42
    Transpose
    0.41
    Gro
    0.40
     mouvement
    0.40
    Activations Density 0.001%

    No Known Activations