© 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-65K
    7. 48338
    Prev
    Next
    INDEX
    Explanations

    DEA, EA, Rea, av, ax

    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
    equiv
    0.45
     Develop
    0.44
    Exercises
    0.43
    Rel
    0.42
     Loose
    0.41
    ೧
    0.40
     \\..
    0.40
    bagian
    0.38
    ᱑
    0.38
    availability
    0.37
    POSITIVE LOGITS
    iness
    0.44
    ured
    0.42
    soever
    0.41
    hea
    0.40
    вез
    0.39
     erken
    0.38
    weaver
    0.38
    ness
    0.37
    htaking
    0.37
    år
    0.37
    Activations Density 0.044%

    No Known Activations