© 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. 53-GEMMASCOPE-2-RES-262K
    7. 39078
    Prev
    Next
    INDEX
    Explanations

    The Purge

    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_53_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
     Jam
    0.42
    钬
    0.40
     Ag
    0.40
     entrega
    0.40
     अहं
    0.39
    क्षी
    0.39
     Film
    0.38
     కావ
    0.38
    )$}
    0.37
     FILM
    0.37
    POSITIVE LOGITS
    meaning
    0.40
    sim
    0.38
    |,
    0.38
     meaningful
    0.38
     meaningfully
    0.37
    '^
    0.37
    Defining
    0.36
    ્યા
    0.36
     meaning
    0.35
    osing
    0.35
    Activations Density 0.001%

    No Known Activations