© 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. 27741
    Prev
    Next
    INDEX
    Explanations

    perspectives, brother, CBD, basics

    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
    zina
    0.47
     Garant
    0.46
     Duss
    0.44
     armor
    0.44
    <unused2113>
    0.44
     educativo
    0.43
    Foi
    0.43
    ッション
    0.43
     ZIP
    0.42
    Vor
    0.42
    POSITIVE LOGITS
     ci
    0.43
     pleasing
    0.43
     defeating
    0.42
     tiring
    0.42
     விரும்ப
    0.42
     refreshing
    0.41
    姑
    0.41
     hydrating
    0.41
     chc
    0.40
     cu
    0.40
    Activations Density 0.000%

    No Known Activations