© 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. 70989
    Prev
    Next
    INDEX
    Explanations

    Fields, archive, visible, digital, vulnerability, simplicity

    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
     ინფორმა
    0.49
     समोर
    0.45
     Bewert
    0.45
    鏉
    0.43
     عمليات
    0.43
     descripción
    0.42
     With
    0.41
     ياس
    0.41
    Comm
    0.41
     بوص
    0.41
    POSITIVE LOGITS
    ckpt
    0.44
    路
    0.43
    deleted
    0.40
    orbit
    0.40
     hastened
    0.40
    umlah
    0.39
     approach
    0.39
     graduated
    0.39
    uia
    0.39
     needy
    0.38
    Activations Density 0.007%

    No Known Activations