© 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. 165021
    Prev
    Next
    INDEX
    Explanations

    Comparison, domain, security, attributes

    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
    魇
    0.41
    句
    0.40
     tort
    0.39
     torture
    0.39
    entretien
    0.38
    Само
    0.38
    dtype
    0.37
    𝔀
    0.37
    manship
    0.37
    б
    0.37
    POSITIVE LOGITS
     عكس
    0.43
     Although
    0.41
    truncated
    0.40
     truncated
    0.40
     Variable
    0.40
     trunc
    0.39
     Bonuses
    0.39
     Recuper
    0.39
     Wealth
    0.38
     Arbit
    0.38
    Activations Density 0.002%

    No Known Activations