© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166731
    Prev
    Next
    INDEX
    Explanations

    describes specific terms

    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_40_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
     strength
    0.42
     straining
    0.40
     molecules
    0.38
     modulating
    0.37
     amplified
    0.37
     strangers
    0.36
    舷
    0.36
     again
    0.35
     audiences
    0.35
     strings
    0.35
    POSITIVE LOGITS
    QUEST
    0.42
     уважа
    0.42
    -¹
    0.41
     continuidade
    0.40
    NPC
    0.40
    STAR
    0.40
     катего
    0.40
    uates
    0.39
    LLCATS
    0.39
    Proposed
    0.39
    Activations Density 0.000%

    No Known Activations