© 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-262K
    7. 135905
    Prev
    Next
    INDEX
    Explanations

    workplace policies and previously disallowed content

    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
    餾
    0.44
     obstáculos
    0.40
    ር
    0.40
    崱
    0.39
    환
    0.38
    負担
    0.38
     に対して
    0.38
    শুক্রবার
    0.38
    り
    0.36
    둘
    0.36
    POSITIVE LOGITS
    某些
    0.43
     whaka
    0.42
     Represent
    0.40
     श
    0.40
     slip
    0.40
     represent
    0.40
     unu
    0.39
    Represent
    0.39
    ꜱ
    0.38
     kilku
    0.38
    Activations Density 0.002%

    No Known Activations