© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    reserve

    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
    ชค
    0.53
    㖮
    0.52
    াদিত
    0.51
    Propagation
    0.51
     congruence
    0.50
     الصل
    0.49
     شعر
    0.49
     reconstructed
    0.48
    Cong
    0.48
    ച
    0.47
    POSITIVE LOGITS
     reserve
    5.34
    reserve
    5.00
     reserves
    4.97
     Reserve
    4.94
    Reserve
    4.94
     резер
    4.75
     RESERVE
    4.75
     rezerv
    4.69
     reserv
    4.66
     Reserves
    4.66
    Activations Density 0.188%

    No Known Activations