© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5899
    Prev
    Next
    INDEX
    Explanations

    against

    np_acts-logits-general · gemini-2.5-flash-lite

    opposition to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಬೇ
    0.36
    वह
    0.35
    anco
    0.33
    ન્ટે
    0.33
     carboxyl
    0.33
    るとき
    0.33
    并通过
    0.32
     ቀ
    0.32
     þei
    0.32
     createApp
    0.31
    POSITIVE LOGITS
     against
    5.16
    against
    4.97
     Against
    4.69
    Against
    4.69
     AGAINST
    4.53
     против
    4.50
     gegen
    4.13
     ضد
    4.06
     tegen
    3.95
     contre
    3.73
    Activations Density 0.443%

    No Known Activations