© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7186
    Prev
    Next
    INDEX
    Explanations

    condemn terrorism

    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_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
    rées
    0.47
     полицей
    0.46
    政治
    0.43
    ونَ
    0.42
    ië
    0.42
    political
    0.42
    催
    0.42
     정치
    0.40
    戦争
    0.40
     colonialism
    0.40
    POSITIVE LOGITS
     TH
    0.47
     Kingston
    0.46
     Hamas
    0.45
     terrorists
    0.44
     Astoria
    0.44
     terrorist
    0.42
     pose
    0.41
     requirements
    0.41
     application
    0.40
     Pose
    0.40
    Activations Density 0.139%

    No Known Activations