© 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. 4379
    Prev
    Next
    INDEX
    Explanations

    ideologies and "-isms"

    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
    k
    0.83
    u
    0.75
    ra
    0.72
    v
    0.70
    os
    0.67
    c
    0.64
    f
    0.64
    h
    0.63
    ok
    0.62
    6
    0.61
    POSITIVE LOGITS
     Marxism
    0.59
    -]
    0.52
     communists
    0.51
     erano
    0.49
     respectivos
    0.49
     Volks
    0.48
    Еще
    0.48
    ]
    0.48
     był
    0.48
    -‘
    0.47
    Activations Density 0.208%

    No Known Activations