© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8096
    Prev
    Next
    INDEX
    Explanations

    fighting against

    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_40_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
     терпе
    0.44
    তায়
    0.42
     OPP
    0.40
    比赛
    0.40
    thorax
    0.39
    震撼
    0.39
    mok
    0.38
    せ
    0.38
    競爭
    0.38
    竞争
    0.37
    POSITIVE LOGITS
     against
    0.79
    Against
    0.76
     fought
    0.76
    against
    0.70
     Against
    0.64
     battles
    0.63
     ضد
    0.60
     waged
    0.59
     против
    0.57
     gegen
    0.57
    Activations Density 0.131%

    No Known Activations