© 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. 17500
    Prev
    Next
    INDEX
    Explanations

    recruiting prospects and commits

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

    Q followed by numbers

    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
     histo
    0.42
     Regular
    0.41
     intermission
    0.41
    menopausal
    0.40
    髹
    0.40
     desplazamiento
    0.40
    புரம்
    0.39
    ewną
    0.39
    承包
    0.39
    ペア
    0.38
    POSITIVE LOGITS
     recruiting
    0.91
     recruits
    0.89
     recruit
    0.88
     Rivals
    0.88
     prospect
    0.79
    招
    0.78
     verbal
    0.77
     commits
    0.77
     recruiters
    0.76
     Recruit
    0.75
    Activations Density 0.040%

    No Known Activations