© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8928
    Prev
    Next
    INDEX
    Explanations

    suspicion, suspense, suspend

    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_16k_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
    이다
    0.40
    ingular
    0.39
    ritable
    0.38
    ья
    0.37
    енти
    0.37
    龧
    0.37
    Mania
    0.36
    奨
    0.35
    corollary
    0.35
    Connected
    0.34
    POSITIVE LOGITS
     SUS
    1.18
    SUS
    1.13
    susp
    1.09
     Sus
    1.07
     sus
    1.05
     susp
    1.05
     sosp
    1.05
     сус
    1.05
    Susp
    1.01
    sus
    1.00
    Activations Density 0.064%

    No Known Activations