© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 165328
    Prev
    Next
    INDEX
    Explanations

    cornerstone and foundation

    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
     பார்ப்ப
    0.42
     statistically
    0.39
     наиболь
    0.39
    nec
    0.38
     Trek
    0.37
    ພາ
    0.37
    InnerText
    0.37
    洸
    0.37
    转移
    0.35
     NATURE
    0.35
    POSITIVE LOGITS
     cornerstone
    1.95
     Cornerstone
    1.50
    corner
    1.32
     corner
    1.30
     foundation
    1.27
    Corner
    1.25
     Corner
    1.16
    foundation
    1.14
     foundations
    1.12
     foundational
    1.11
    Activations Density 0.037%

    No Known Activations