© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 58942
    Prev
    Next
    INDEX
    Explanations

    Cold War

    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_all/layer_41_width_262k_l0_big
    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
     chub
    0.37
     Literary
    0.37
    赭
    0.37
     carn
    0.36
     QUILL
    0.36
     INTEGER
    0.36
     देशभर
    0.35
    Academy
    0.35
     साहित्य
    0.35
     Trauma
    0.35
    POSITIVE LOGITS
     Cold
    2.77
    Cold
    2.66
     cold
    2.38
    冷
    2.22
    cold
    2.13
     कोल्ड
    1.90
     冷
    1.84
     냉
    1.75
     холо
    1.73
     холод
    1.73
    Activations Density 0.001%

    No Known Activations