© 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. 16-GEMMASCOPE-2-RES-262K
    7. 6167
    Prev
    Next
    INDEX
    Explanations

    political and social groups

    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_16_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
     be
    0.45
    4
    0.42
    ü
    0.40
    2
    0.38
    8
    0.38
     is
    0.38
    3
    0.38
    5
    0.37
     was
    0.36
    0
    0.36
    POSITIVE LOGITS
    ಲಯ
    0.36
    ানন্দ
    0.35
    ्रू
    0.33
    орк
    0.33
    yiz
    0.33
    ycznych
    0.33
    תיים
    0.33
    tochy
    0.32
    čkog
    0.31
     Anch
    0.31
    Activations Density 0.000%

    No Known Activations