© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7177
    Prev
    Next
    INDEX
    Explanations

    Jehovah's Witnesses, Loving Hut, cults, survival

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     };
    0.61
     inflam
    0.57
    フト
    0.54
     समस्त
    0.53
    }};
    0.52
     }}
    0.50
     sej
    0.49
    glades
    0.49
     });
    0.48
     cliche
    0.48
    POSITIVE LOGITS
     Jehovah
    1.02
     Jehova
    0.87
     Jehová
    0.86
    Jeh
    0.84
     Witnesses
    0.77
     Kingdom
    0.68
     Awake
    0.66
     prophecies
    0.64
     तुलसी
    0.63
     apostle
    0.63
    Activations Density 0.049%

    No Known Activations