© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191158
    Prev
    Next
    INDEX
    Explanations

    general controls and grounding

    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
     întreb
    0.50
     ऐप
    0.48
    洖
    0.44
     மரிய
    0.41
     zwölf
    0.41
    众多
    0.41
     '&
    0.40
     ८
    0.39
    ()!=
    0.39
    řich
    0.39
    POSITIVE LOGITS
     isolate
    0.42
     isolated
    0.42
     extraction
    0.41
     contamination
    0.39
     Hu
    0.38
     Over
    0.37
     erosion
    0.37
     upset
    0.37
     isolating
    0.37
     mechanics
    0.37
    Activations Density 0.001%

    No Known Activations