© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7610
    Prev
    Next
    INDEX
    Explanations

    bet prefix

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

    betrayal

    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
    
    0.45
     সম্পাদিত
    0.38
    ieniem
    0.38
    cible
    0.37
    atici
    0.37
    페이스
    0.37
     మర
    0.36
    穗
    0.36
    采样
    0.35
    MSS
    0.35
    POSITIVE LOGITS
     bet
    1.06
     Bet
    1.00
    Bet
    0.97
     bets
    0.96
    bet
    0.84
     BET
    0.82
    Bets
    0.81
     Bets
    0.80
     betas
    0.79
     betting
    0.74
    Activations Density 0.020%

    No Known Activations