© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41677
    Prev
    Next
    INDEX
    Explanations

    political debate

    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_31_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
    內
    0.43
    उ
    0.40
     বিহ
    0.40
    कु
    0.39
    ﭘ
    0.39
    橡
    0.37
    ಢ
    0.37
     ndani
    0.37
    内
    0.37
    ᱟ
    0.37
    POSITIVE LOGITS
     televised
    0.57
     debates
    0.56
     debating
    0.53
     moderators
    0.52
    debate
    0.52
     semantic
    0.51
     viewers
    0.50
     debate
    0.50
     moderator
    0.48
     probes
    0.48
    Activations Density 0.015%

    No Known Activations