© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135140
    Prev
    Next
    INDEX
    Explanations

    religious freedom and suppression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
     melamine
    0.41
    🥵
    0.41
    ONG
    0.39
    विध
    0.39
    jem
    0.38
     lentement
    0.38
     pozit
    0.38
     ऑफिशियल
    0.37
     Peng
    0.37
     الطرف
    0.36
    POSITIVE LOGITS
    ጦ
    0.46
     religiosos
    0.42
     asserts
    0.38
     অষ্টম
    0.38
    ندان
    0.38
     inscr
    0.38
     asserted
    0.37
    出して
    0.37
     religion
    0.37
     relig
    0.37
    Activations Density 0.002%

    No Known Activations