© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14857
    Prev
    Next
    INDEX
    Explanations

    Technical text or data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     उम्मीद
    0.63
    Cory
    0.57
    額
    0.56
     একাডেমিক
    0.55
     chrom
    0.55
     dave
    0.54
     Enrique
    0.53
    Hod
    0.53
     Hod
    0.53
    noy
    0.53
    POSITIVE LOGITS
     Vapor
    0.66
     রসের
    0.60
    руп
    0.59
     refiere
    0.52
    ꯦ
    0.51
     Sampling
    0.50
     гульнявыя
    0.50
    wała
    0.50
     সালাম
    0.50
    iap
    0.49
    Activations Density 0.000%

    No Known Activations