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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2140
    Prev
    Next
    INDEX
    Explanations

    InternetArchiveBot

    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_65k_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
     တ
    0.52
     ထ
    0.46
    ော
    0.46
    𝕂
    0.44
    ᒫ
    0.43
     शिश
    0.42
     လ
    0.42
     Bankr
    0.42
     एम
    0.41
     ふ
    0.41
    POSITIVE LOGITS
     IPL
    0.50
     i
    0.49
     ICA
    0.48
     IEM
    0.46
     ICC
    0.45
     IBA
    0.42
     ia
    0.42
     IAF
    0.41
     IM
    0.41
     IPM
    0.41
    Activations Density 0.377%

    No Known Activations